ArticlePDF Available

Landslide susceptibility mapping of the Sera River Basin using logistic regression model


Abstract and Figures

Of the natural hazards in Turkey, landslides are the second most devastating in terms of socio-economic losses, with the majority of landslides occurring in the Eastern Black Sea Region. The aim of this study is to use a statistical approach to carry out a landslide susceptibility assessment in one area at great risk from landslides: the Sera River Basin located in the Eastern Black Sea Region. This paper applies a multivariate statistical approach in the form of a logistics regression model to explore the probability distribution of future landslides in the region. The model attempts to find the best fitting function to describe the relationship between the dependent variable, here the presence or absence of landslides in a region and a set of independent parameters contributing to the occurrence of landslides. The dependent variable (0 for the absence of landslides and 1 for the presence of landslides) was generated using landslide data retrieved from an existing database and expert opinion. The database has information on a few landslides in the region, but is not extensive or complete, and thus unlike those normally used for research. Slope, angle, relief, the natural drainage network (including distance to rivers and the watershed index) and lithology were used as independent parameters in this study. The effect of each parameter was assessed using the corresponding coefficient in the logistic regression function. The results showed that the natural drainage network plays a significant role in determining landslide occurrence and distribution. Landslide susceptibility was evaluated using a predicted map of probability. Zones with high and medium susceptibility to landslides make up 38.8 % of the study area and are located mostly south of the Sera River Basin and along streams.
This content is subject to copyright. Terms and conditions apply.
1 23
Natural Hazards
Journal of the International Society
for the Prevention and Mitigation of
Natural Hazards
ISSN 0921-030X
Nat Hazards
DOI 10.1007/s11069-016-2591-7
Landslide susceptibility mapping of the
Sera River Basin using logistic regression
Nussaïbah B.Raja, Ihsan Çiçek, Necla
Türkoğlu, Olgu Aydin & Akiyuki
1 23
Your article is protected by copyright and all
rights are held exclusively by Springer Science
+Business Media Dordrecht. This e-offprint
is for personal use only and shall not be self-
archived in electronic repositories. If you wish
to self-archive your article, please use the
accepted manuscript version for posting on
your own website. You may further deposit
the accepted manuscript version in any
repository, provided it is only made publicly
available 12 months after official publication
or later and provided acknowledgement is
given to the original source of publication
and a link is inserted to the published article
on Springer's website. The link must be
accompanied by the following text: "The final
publication is available at”.
Landslide susceptibility mapping of the Sera River Basin
using logistic regression model
¨bah B. Raja
Ihsan C¸ic¸ek
Necla Tu
Olgu Aydin
Akiyuki Kawasaki
Received: 25 August 2015 / Accepted: 20 September 2016
ÓSpringer Science+Business Media Dordrecht 2016
Abstract Of the natural hazards in Turkey, landslides are the second most devastating in
terms of socio-economic losses, with the majority of landslides occurring in the Eastern
Black Sea Region. The aim of this study is to use a statistical approach to carry out a
landslide susceptibility assessment in one area at great risk from landslides: the Sera River
Basin located in the Eastern Black Sea Region. This paper applies a multivariate statistical
approach in the form of a logistics regression model to explore the probability distribution
of future landslides in the region. The model attempts to find the best fitting function to
describe the relationship between the dependent variable, here the presence or absence of
landslides in a region and a set of independent parameters contributing to the occurrence of
landslides. The dependent variable (0 for the absence of landslides and 1 for the presence
of landslides) was generated using landslide data retrieved from an existing database and
expert opinion. The database has information on a few landslides in the region, but is not
extensive or complete, and thus unlike those normally used for research. Slope, angle,
relief, the natural drainage network (including distance to rivers and the watershed index)
and lithology were used as independent parameters in this study. The effect of each
parameter was assessed using the corresponding coefficient in the logistic regression
function. The results showed that the natural drainage network plays a significant role in
determining landslide occurrence and distribution. Landslide susceptibility was evaluated
using a predicted map of probability. Zones with high and medium susceptibility to
landslides make up 38.8 % of the study area and are located mostly south of the Sera River
Basin and along streams.
Keywords Landslide Susceptibility Logistic regression Geographical information
systems (GIS) Turkey
&Olgu Aydin;
Department of Geography, Faculty of Humanities, Ankara University, 06100 Sıhhıye/Ankara,
Department of Civil Engineering, The University of Tokyo, Tokyo 153-8505, Japan
Nat Hazards
DOI 10.1007/s11069-016-2591-7
Author's personal copy
1 Introduction
Landslides are one of the most important geohazards, causing economic and social losses
as well as damage to soil and water resources (Schlogel et al. 2015; Korup et al. 2012
Alimohammadlou et al. 2013). Worldwide, landslides account for 17 % of all deaths
caused by natural hazards (Herath and Wang 2009; Kjekstad and Highland 2009). Rapid
growth and urbanisation in the developing world as well as a changing climate are among
the main reasons for the observed global increase in landslides. In Turkey, landslides
triggered by both social and physical factors are the second most dangerous natural hazard
in terms of socio-economic losses (Demir et al. 2015a,b). US$ 80 million of property is
lost each year in Turkey due to landslides (Yalcin 2011,2007). Moreover, a considerable
amount of fertile land is carried away yearly by rivers as a result of soil erosion, which
leaves the remaining fertile land exposed to increased erosion and landslides (Irvem et al.
2007; Aydin and Tecimen 2010). Such environmental hazards have been exacerbated by
disorganised and traditional land use practices in rural areas, where planning and land
management regulations are often disregarded (Demir et al. 2015b).
Landslides are a continuing problem in the Eastern Black Sea Region, especially in the
Trabzon province where about 64 % of the region is at risk from landslides (Reis et al.
2009). From 2005 to 2008, 178 landslides occurred in areas with heavy rainfall and steep
slopes (Bayrak and Ulukavak 2009). Several landslide-related studies have been conducted
in the last decade for this region of the Black Sea (Demir et al. 2015b; Bayrak and
Ulukavak 2009; Yalcin 2007; Nefeslioglu et al. 2008; Yalcin et al. 2011; Reis et al. 2009),
with deforestation, population increase, extreme precipitation, topography, geology, river
networks and land use being some of the observed factors that contribute to landslide
activity. Widespread agriculture (hazelnuts and tea are cultivated) makes the Trabzon
province an economically important region for Turkey. Also, the region, which is located
on the legendary Silk Road, is an important hub for tourism and trade, registering an
increase in ecotourism in the past decade (Reis et al. 2009; Cavus 2014).
Landslides occur regularly in the Sera River Basin, the designated study area of this
paper. However, only a few relevant studies have been carried out in the area. The study
area is located in the western part of the Eastern Black Sea region in the county of
Akc¸aabat, southwest of the city of Trabzon, one of the most important harbour cities in
Turkey. Landslides in this region are triggered both naturally and artificially. Natural
triggers constitute heavy precipitation, stream erosion of slope toes and weathering of the
bedrock. Artificial triggers include steep and improperly cut slopes, poorly controlled
surface drainage, and uncontrolled settlement and agricultural activities. Landslide activity
is currently concentrated in one area, north of Lake Sera. Nonetheless, it is believed that
the spatial distribution of landslides is likely to increase as a result of extreme precipitation
events in the Eastern Black Sea, and severe deforestation to accommodate more agriculture
and infrastructure. For the purposes of disaster and risk management, an assessment of
landslide susceptibility in the Sera River Basin is imperative.
Landslide susceptibility can be defined as the propensity of an area to generate land-
slides (Guzzetti et al. 2006). Several techniques can be employed for hazard modelling.
These mainly fall into four categories: (1) expert evaluations, (2) statistical methods, (3)
non-deterministic models and (4) mechanical approaches (deterministic or numerical
models). While expert evaluation methods are the most common approach used to evaluate
landslide hazards (Sarkar and Anbalagan 2008; Raghuvanshi et al. 2014; Kayastha et al.
2013), the subjectivity of decision making means there is a need for more sophisticated
Nat Hazards
Author's personal copy
techniques to be integrated into the overall methodology. A way to reduce bias is to include
statistical approaches (Fall et al. 2006). Since such methods are also relatively easy to
implement in geographical information systems (GIS) (Kawasaki et al. 2001; Pradhan
2013), an increasing number of studies have adopted statistical approaches such as
bivariate and multivariate analysis including logistic regression, for landslide susceptibility
mapping (Zhuang et al. 2015; Nefeslioglu et al. 2008; Akgun et al. 2011; Mancini et al.
2010; Althuwaynee et al. 2014; Schicker and Moon 2012; Youssef et al. 2015; Bui et al.
2011; Hina et al. 2014). Many non-deterministic models are designed to overcome the
complexity of landslide susceptibility mapping (matter-element model, fuzzy set methods,
artificial neural network, fuzzy models) and have been employed in several studies con-
cerning landslide hazard assessment (Wu et al. 2003; Bui et al. 2012; Pradhan 2011a,b;
Shahabi et al. 2012; Zare et al. 2013; Wu et al. 2014). Mechanical approaches, on the other
hand, use deterministic and/or numerical models that assess slope stability to evaluate
landslide hazards (De Vita et al. 2013; Jia et al. 2012; Armas et al. 2013; Notti et al. 2015).
Despite the effectiveness of non-deterministic and machine learning methods that consider
complex classification problems, these methods have a steep learning curve. Furthermore,
some of these methods can only be implemented using specific software.
The aim of this study was to carry out a landslide susceptibility assessment using a
statistical approach for one of the regions in Turkey most at risk from landslides: the Sera
River Basin. This area was chosen as it is at high risk of landslides and also shows high
potential for tourism and recreation by local authorities (Cavus 2014; Bayrak and Ulu-
kavak 2009). Tourist traffic to the Sera Lake and surrounding areas has led to more
settlement in the region. In addition, quarrying operations are currently being carried out
on land displaced by a landslide in 1950. The probability of landslide activity in the area
has increased considerably as a result of vibrations from these operations. In identifying the
areas sensitive to landslides, existing residential regions that are at risk and areas suit-
able for future settlement could be identified. Using data about past landslides, the study
developed a tool to produce a landslide probability map. The binary logistic regression
used in this study is one of the most popular statistical methods for determining landslide
susceptibility and has often been applied for this purpose (Suzen and Doyuran 2004;
Ercanoglu and Temiz 2011; Akgun 2012). The application of logistic regression requires
the inclusion of landslide triggering and/or conditioning parameters as independent vari-
ables. In general, the more independent variables that are included, the more complete the
model will be, given that the consideration of variables plays a major role in determining
the dependent variable. According to Coe et al. (2000) and Fabbri et al. (2003), limited
data, if of sufficiently high quality, can produce more accurate results as compared to more
information of poorer quality. The main advantage of this method is therefore its ability to
evaluate the significance of causative factors while eliminating those factors which are
unrelated (Yesilnacar and Topal 2005; Chauhan et al. 2010; Ghosh et al. 2011). The study
involved the derivation of a landslide probability equation which considers topographic,
hydrological and geological parameters by applying logistic regression analysis to the
modelling area. The equation was then validated by applying it to the whole of the Sera
River Basin. Also, while most studies carried out in Trabzon province are on the regional
scale (Yalcin et al. 2011; Reis et al. 2009), few focus on small-scale landslide hazard
mapping (Akgun and Bulut 2007; Yalcinkaya and Bayrak 2005), which is helpful for those
making administrative decisions in the region.
Nat Hazards
Author's personal copy
2 Study area
The Sera River Basin, with an area of 73.75 km
, is located west of the Trabzon province,
which is in the administrative boundaries of the county of Akc¸aabat. The basin is 2 km
inland from the coast, between latitudes 40°520000–41°003000 N and longitudes 39°310000
39°390000E (Fig. 1). It lies within the Eastern Black Sea Region Watershed, part of the
Caucasus Ecologic Region, which is one of the five biologically diverse world regions as
identified by the World Wildlife Fund (WWF) and thus is of international importance
(WWF 2015).
Lake Sera, situated in the north of the basin, was formed as a result of a landslide in
1950 and is now a nature reserve and tourist destination in Turkey. The Sera Landslide
occurred on 21 February 1950, about 2.5 km inland from the coast. It resulted in about 15
million m
of land being displaced, making it one of the most significant landslides seen in
the Eastern Black Sea Region. A week before the event, several signs of an impending
landslide were observed, mainly in the form of long and deep cracks. The landslide was
due to intensive chemical disintegration in the geomorphological structure of the region as
a result of the presence of deep fissures in basaltic and andesitic lava formations from the
Upper Cretaceous period (Fig. 2). This disintegration caused instability and susceptibility
to moisture from higher-than-expected rainfall and the sudden melting of snow due to
Fig. 1 Location and topography of the Sera River Basin
Nat Hazards
Author's personal copy
southern Foehn winds, which caused a significant amount of water to leak into the ground.
The landslide, 220 m from foot to crown, is believed to have stemmed from the largest
crack. The flow of land was complex, with three landslide types identified, namely single
block slides, multiple rotational block slides and topple failures. The landslide created a
wall from west to east that blocked the valley and the Sera River and led to the formation
of a dam/lake. This endorheic basin is about 4 km long, 200 m wide and 50 m deep
(Boztas 1986).
The topography of the basin has an average slope of 23°. The average precipitation in
this region is 822 mm, considerably more than that for Turkey as a whole (643 mm). As in
the rest of the Black Sea Region, subsistence/semi-subsistence farming is common, but
there is little large-scale commercial farming as a result of the topography and land
ownership issues (Inan et al. 2011; Demir et al. 2015b). Areas north and south of the lake
have seen major infrastructure development with the construction of buildings and roads.
This construction is believed to have been stimulated by tourism (Fig. 3). Ongoing soil
erosion and conversion of land for agriculture and infrastructure has resulted in an increase
in the frequency of landslides in the active landslide zone. Currently, this area is 0.12 km
but it might grow if current practices are not controlled. The last known landslide, along
the site of a new road, is believed to have occurred in March–April 2015.
Fig. 2 Cross section of the active landslide zone of the Sera River Basin Source: Sarıyılmaz (1972)
Fig. 3 Aerial view of Lake Sera. Areas north and south of the Basin have seen considerable development
leading to deforestation of the forest around thus increase landslide risks. The red line designates the extent
of the Sera River Basin and yellow the presently active landslide zone Source: Images obtained from Google
Nat Hazards
Author's personal copy
3 Input data sources
3.1 Landslide data
The application of logistic regression for the purpose of landslide susceptibility mapping
requires a reliable inventory of the type, activity and spatial distribution of all landslides in
the study area. However, in Turkey these inventories are not common (Akgun and Bulut
2007). The existing database of landslides in the region, obtained from national catalogues,
includes only the 1950 landslide which led to the creation of Lake Sera. These data are in
polygon form and may include debris runout zones, which would lead to an overestimation
of the landslide source region. Post-1950, landslide activity in the Sera River Basin has
been continuous, occurring regularly especially over the past 5 years as a result of the
aforementioned reasons. In the absence of a complete landslide inventory, expert opinion
was employed to map landslide activity (Fig. 4). This map shows that landslides of the
slide type are the most common in the area. Because this study is based on limited data,
this landslide susceptibility assessment should be considered preliminary until a landslide
database is developed and a more advanced study is possible.
3.2 Landslide factors
Factors affecting slope stability are various and are in most cases interconnected. The main
trigger factor for landslides in the study area and most of the Black Sea region is heavy
precipitation due to the increase in precipitation extremes and intensity observed (Can et al.
Fig. 4 Landslide and model area of the Sera River Basin
Nat Hazards
Author's personal copy
2005; Yalcin and Kavurmaci 2013). The influence of precipitation on landslides differs
depending on landslide type, dimension, kinematics and material involved. Shallow fail-
ures, often occurring in the Sera River Basin, are usually triggered by short intense storms
(Guzzetti et al. 1992; Flentje et al. 2000; Can et al. 2005). Because precipitation is rela-
tively uniform throughout the study area, it was not included in the regression analysis as
its effect is negligible. Seismicity was not considered for the same reason. River incision
and aggradation may occur as a result of tectonics and thus influence susceptibility to
landslides leading to changes in the river courses and local topography (Dunning et al.
2007; Pirasteh et al. 2009). Roads were excluded because they are few. In the eastern part
of the study area, there is a single road, running parallel to the Sera River. Land use is the
main reason for anthropologically induced instability in the Sera River Basin. Land use
pattern has been changing in this region in terms of agricultural needs and settlement area
in order to cater for the increase in population. The deforestation of the native broadleaf
forests has made this region more prone to landslides, especially in cleared and sparsely
vegetated areas. However, the unavailability of current and accurate details of land use
change in the region prevented the inclusion of this parameter. Similarly, no data were
available on weathering of the bedrock and erosion of the slope toes and other soil
properties. The spatial variation in slope stability and hydrological conditions, including
soil moisture and groundwater flow, is controlled mainly by topographic conditions. As
such, topographic indices such as the topographic wetness index (TWI) can be used to
describe spatial soil moisture patterns (Yilmaz 2009). Subsequently, the analysis consid-
ered the following landslide-conditioning parameters: profile curvature, slope, aspect,
relative relief, distance to rivers, topographic wetness index and lithology.
Supporting data for this study was obtained from 1:25,000-scale topographic maps and
1:100,000-scale geological maps prepared by the General Directorate of Mineral Research
and Exploration of Turkey. Contour lines that contain elevation values were extracted from
the topographic map, after which a digital elevation model (DEM) with cell size
25 m 925 m was constructed. Slope, aspect, relief, profile curvature and topographic
wetness index values were calculated using the DEM. Geologic maps were scanned and
then digitised in ArcGIS to prepare the lithology. All the data layers mentioned below in
the context of logistic regression analysis are shown in Fig. 5.
3.2.1 Profile curvature
Most slopes are not uniform but rather consist of a sequence of convex, concave and
uniform areas, whose effect on sediment load and erosion is not properly reflected by
overall average steepness (Di Stefano et al. 2000). The profile curvature refers to the
curvature of the land surface in the direction of the steepest slope, with respect to the
vertical plane of a flow line. The profile curvature affects the rate at which water drains
from the surface and influences erosion and deposition. Erosion is more likely to be
prominent in areas transitioning from convex (negative) and flat profile curvature to
concave (positive) curvature while deposition occurs in places with convex surfaces
(Alkhasawneh et al. 2013; Cavalli et al. 2016). Curvature was classified into three classes:
concave (\0), flat (0) and convex ([0).
3.2.2 Slope and aspect
Slope and aspect are significant conditioning parameters of small-scale landslides (Lee and
Min 2001; Dai and Lee 2002). Slope angle is used regularly in landslide susceptibility
Nat Hazards
Author's personal copy
studies as it is one of the primary causes of landslides (Lee 2005; Yalcin 2008; Nefeslioglu
et al. 2008), while aspect is also an important factor in assessing landslide hazard sus-
ceptibility (Yalcin and Bulut 2007; Galli et al. 2008). Aspect is associated with parameters
such as exposure to sunlight, drying winds and rainfall, which may affect the location of
landslides (Suzen and Doyuran 2004). The slope and aspect parameters for the model and
validation area were extracted from the DEM. The overall slope was classified into five
Fig. 5 Data layers used in the logistic regression analysis. aSlope, baspect, cprofile curvature, drelative
relief, elithology, fdistance to river, gTWI
Nat Hazards
Author's personal copy
classes: \10°,10°–20°,20°–30°,30°–40°and [40°. The aspect was also divided into five
classes: flat (-1°), north (0°–45°and 315°–360°), east (45°–135°), south (135°–225°) and
west (225°–315°).
3.2.3 Relative relief
Relative relief refers to the elevation range between the lowest and highest points of a
region and is an important parameter in landslide hazard mapping. Landslide susceptibility
increases as relief increases, but at different levels with different geology (Dai et al. 2001;
Zhu et al. 2014). Bedrock incision caused by rivers can generate sufficient relief to pre-
dispose slopes to catastrophic land mass failures (Korup et al. 2007). The steepening of
hillslopes by erosion leads to an increase in relief above a threshold value and landslides
follow. Relief was divided into five classes:\50, 50–100, 100–150, 150–200 and[200 m.
3.2.4 Distance to river
The Sera River is a key feature of the Sera River Basin. Previous studies show that
landslides tend to occur along the sides of valleys as a result of groundwater flowing
towards streams and rivers, which in turn affects undercutting processes (Korup et al. 2007;
Tang et al. 2011; Zaruba and Mencl 2014). In this study only first- and second-order rivers
were considered as low-order streams are less important in the landslide process (Fan et al.
2013; Othman and Gloaguen 2013). Distance to river was calculated in ArcGIS and
categorised into five classes: \250, 250–500, 500–1000, 1000–2000 and [2000 m.
3.2.5 Topographic wetness index (TWI)
Topographic indices, such as TWI, are used to describe soil moisture distribution and
groundwater flow (Beven and Kirkby 1979; Moore et al. 1991). Therefore, it is important
to account for TWI when considering landslide processes (Pourghasemi et al. 2012;
Timilsina et al. 2014). TWI is defined as:
TWI ¼ln As
tan b
 ð1Þ
where A
is the specific catchment area (the local upslope area draining through a certain
point per unit contour length) and bis the slope. TWI is usually higher in flat, converging
terrain and lower in regions of steep, diverging land (Timilsina et al. 2014). TWI values
were normalised for a scale of 1–10 (1 the lowest, 10 the highest) and classified into six
classes: \2, 2–4, 4–5, 5–6, 6–8 and [8.
3.2.6 Lithology
Rock permeability and strength are characterised by geological parameters such as
lithology and structure. Therefore, determining rock boundaries and their overall distri-
bution is important when considering landslide processes (Ayalew and Yamagishi 2005).
Lithological data were grouped into five main domains (Table 1), and these were used for
Nat Hazards
Author's personal copy
4 Materials and methods
The ArcGIS software was used to prepare data and represent modelling results, while the R
statistical programme (R Development Core Team 2015) enabled logistic regression
analysis (modelling and validation processes of the study area). The flowchart showing the
different steps of the study is illustrated in Fig. 6.
4.1 Sample selection
Instead of using a single point to represent one landslide, this study considered the whole
area of moved landslide masses from the previous landslides. This is because single points
tend to not fully represent the characteristics of the landslide area (Timilsina et al. 2014).
Previous studies also show that sampling patterns are best when ‘‘seed cells’’ or gridded
points extracted from the landslide area are used to obtain attributes for landslide and
random landslide-free points (Brenning et al. 2005; Meusburger and Alewell 2009; Van
Den Eeckhaut et al. 2010). However, given the limited data considered in this study, the
small sample may not fully cover the diversity of all the factors in the study area, on which
the resulting model is dependent (Heckmann et al. 2014).
Addressing the issue of ‘‘rare events’ when applying logistic regression, King and Zeng
(2001) state that the number of non-events should typically be 2–5 times higher than that of
events for the model area (Heckmann et al. 2014). In addition, they propose endogenous
stratified sampling, that is, a sampling method that includes all events and a random sample
of non-events. The sample selection of this study followed the reasoning of King and Zeng
(2001): all the landslides events and a random sample of non-events around the current
landslide active area were chosen. As shown in Fig. 4, of the 24,768 gridded points in the
model area defined, 5992 were classified as landslide points (event points, 1) and 18,776
(non-event points, 0) as landslide-free points, giving a ratio of approximately 1:4.
4.2 The modelling strategy
Logistic regression allows the analysis of a problem where the result, measured with
dichotomous variables such as 1 and 0 (or TRUE and FALSE), is determined from one or
more independent factors (Menard 2002). Consideration of the influence of nindependent
variables (x
to x
) on the dependent variable (Y) generates the model statistics and
Table 1 Lithology domains and rock formations of the study region
Age Rock formation Description
1. Qal Quaternary Alluvium Gravel, sand, clay
2. Tb Pliocene Besirli Formation Sandstone, mudstone, conglomerate,
basalt, agglomerate
3. Tek Eocene Kabakoy
Andesite, basalt and their
pyroclastics, sandy limestone, tuff
4. KTb Palaeocene–Lower
Sandstone, marl, shale, clayey
limestone, tuff
5. Pzm Palaeozoic Metamorphic
Gneiss, mica schist, chlorite schist
Nat Hazards
Author's personal copy
coefficients of a formula used to predict the probability of a logit transformation of the
dependent variable. As such, logistic regression results do not define landslide suscepti-
bility directly. Instead, an inference can be drawn using the probability values. In the case
of landslide susceptibility mapping, logistic regression attempts to determine the model
that best describes the relationship between the presence or absence of the dependent
variable (landslides) and a set of independent variables. There are no universal criteria or
guidelines for the selection of independent variables, although there is a general agreement
that they should have a certain degree of affinity with the dependent variable, be fairly
represented across the study area, vary spatially within the study area and be measurable
(Ayalew and Yamagishi 2005). The independent variables employed in this study are
Fig. 6 Flowchart of the study
Nat Hazards
Author's personal copy
slope, aspect, relief, lithology, distance to rivers and TWI, respectively. The independent
variables can be continuous or categorical, but the latter was preferred here. With regard to
the categorisation of the variables, the range of each class does not greatly affect the
landslide hazard prediction capacity (Remondo et al. 2003), so both expert-based and
landslide distribution-based classifications are applicable. Furthermore, due to the addition
of an appropriate function to the usual linear regression model, the variables may either be
continuous or discrete, or a combination of both types, and do not necessarily have normal
distribution (Lee and Sambath 2006).
Logistic regression coefficients can be used in the model to estimate the effect of each
of the independent variables on landslide occurrence (Pradhan and Lee 2010; Ayalew and
Yamagishi 2005). While regression coefficients are not readily interpretable, standardised
coefficients can be used to assess the relative importance of predictors (Ma
˘rint et al.
2013). In addition, the data firstly need to be normalised in order to generate an accurate
model; combining data with different measuring scales can lead to problems in the
interpretation of final results. The logistic regression model allows the integration of both
continuous and discrete independent variables. In this study, all continuous variables were
converted to discrete variables according to their classes. Categorical variables can be
integrated into two ways: (1) by expressing the classes of each discrete parameter as
dummy variables (Guzzetti et al. 1999; Dai and Lee 2002; Nefeslioglu et al. 2008) or (2) by
computing landslide densities for discrete parameters and using these as the density pre-
dictors (Zhu and Huang 2006; Yilmaz 2009). This study used the latter approach to prevent
the creation of an excessively high number of dummy variables. Use of landslide densities
also allows for the representation of independent parameters on the same scale (Ayalew
and Yamagishi 2005). Landslide densities for slope, aspect, relief, curvature, lithology,
distance to rivers and TWI were computed using the following formulae (Bai et al. 2010):
LA=AðÞ ð2Þ
where LD
is the landslide density value for class i,LA
and A
are the landslide area in
class iand the total area of class i, respectively, and LA and Aare the total landslide area in
the model region and the total area of the model region, respectively. A class with a high
landslide density corresponds with a parameter having a higher coefficient in the logit
function and hence is considered to play a greater role in landslide activity.
Therefore, the logit function that defines the probability of a landslide occurring (P)is
expressed as:
logit ¼ln P
and hence,
ðÞ ð4Þ
where b0...bnare constants.
The regression coefficients are computed using the maximum likelihood estimation
(Suzen and Doyuran 2004). Compared with linear regression, there is no unique solution
for logistic regression coefficients, hence why the maximum likelihood estimation follows
an iterative algorithm.
Nat Hazards
Author's personal copy
For the susceptibility model, 80 % of the landslide and non-landslide points were used
as training samples. The remaining 20 %, randomly selected, were used as an independent
data set for validation and for testing the predictive potential of the logistic regression
model. Continuous susceptibility values, obtained from the model and ranging from 0 to 1,
were classified into five classes. Several approaches can be taken in this regard including
equal intervals, standard deviation-based separations, natural breaks method and quantiles.
There is, however, no agreement on the best method. Ayalew and Yamagishi (2005) state
that the use of equal intervals tends to emphasise one class over the other and recommend
the standard deviation approach as the best choice for class separation. Conversely,
˘rint et al. (2013) recommend the natural breaks algorithm (Jenks 1977) which groups
similar values together thus maximising the differences between classes. This method was
applied here and five landslide susceptibility classes were chosen, namely very low, low,
medium, high and very high.
4.3 Evaluation
The goodness of fit for the susceptibility model was tested with the pseudo-R
, the
R2, the Brier score and the area under the curve (AUC) of the receiver
operating characteristic (ROC).
The Nagelkerke
R2can be interpreted as the proportion of explained variation in the
regression model. Therefore, it can be used as a measure of success with regard to pre-
dicting the dependent variable from the independent variables (Nagelkerke 1991).
R2is defined as:
max R2
ðÞ ð5Þ
max R2
where L^
and L(0) represent the fitted models with the independent variables and the
‘null’’ model fitted with only the intercept, respectively.
The Brier score provides a means of assessing relative accuracy and generates the ‘‘error
rate’ of the logistic regression model (Brier 1950). The formulation of the Brier score is as
BS ¼1
where f
is the probability forecasted in Eq. 3,o
is the observed outcome of the event at
instance tand Nis the number of forecasting instances. The Brier score ranges from 0 to 1
and measures the mean squared difference between the predicted probability and the
observed outcome. Therefore, a completely accurate forecast would generate a value of 0.
Nat Hazards
Author's personal copy
Wald statistics, which evaluate the statistical significance of each coefficient b
in the
model, were calculated as follows:
where W
represents the Wald test and SEbjrepresents the standard error of coefficient b
for independent variable j.
Classification accuracy tables and the ROC methodology were used as validation for
both the training and test samples. The ROC curve is a useful method for representing the
quality of deterministic and probabilistic detections and forecast systems (Swets 1988). It
analyses the relationship between sensitivity and specificity of a binary classifier, in this
instance the occurrence of landslides. Sensitivity refers to the proportion of positives
correctly classified, that is, the proportion of landslides correctly identified when com-
paring predicted probability to observed values. Specificity measures the proportion of
negatives correctly classified, that is, the proportion of landslide-free regions correctly
identified (Flach 2010; Yesilnacar and Topal 2005). Conventionally, the curve is a plot of
the probability of a correctly predicted response to an event (true positive rate or sensi-
tivity) versus the probability of a falsely predicted response to an event (false positive rate
or 1-specificity), as the cut-off probability varies and in other words correctly predicting a
landslide at a certain location, and incorrectly predicting a landslide at a certain location.
The AUC evaluates the quality of the forecast system by describing the ability of the
system to anticipate correctly the occurrence or non-occurrence of pre-defined ‘‘events’’, in
this case landslides. AUC is measured on a scale of 0 and 1. When AUC =1, every
positive has scored higher than every negative and the forecast is completely accurate—the
model is ideal. Excellent models have AUC values greater than 0.9 and good models AUC
values greater than 0.7 (Ma
˘rint et al. 2013).
5 Analysis and results
5.1 Landslide susceptibility model
Landslide densities were computed for each class of landslide-conditioning parameters
(Table 2), and these values were used in the logistic regression analysis. With regard to
slope angle, the highest landslide density values corresponded with angles of more than
40°. Higher landslide density values were also associated with eastern and western slopes,
concave curvature, higher TWI values (2–8), areas within 500 m of rivers and, in terms of
lithology, KTb and Tb.
The logistic regression coefficients and standardised coefficients obtained are given in
Table 3. The slope aspect in the ‘‘West’’ class has the highest coefficient, indicating its
strong influence, followed by distance to rivers (under 500 m) and slope angles (greater
than 40°). With regard to slope aspect, the ‘‘north’’ class produced the second highest
coefficient. This indicates that landslides in the Sera River Basin are first and foremost
related to slope characteristics and proximity to rivers, then lithology.
Nat Hazards
Author's personal copy
5.2 Landslide susceptibility mapping
After the logistic regression modelling, the susceptibility values were classified from very
low to very high according to the natural breaks method algorithm. The upper threshold
values are presented in Table 4. This table shows that the very low and low susceptibility
classes account for 43.5 and 17.7 % of the study area. Conversely, about 27 % of the study
area is highly/very highly susceptible. Figure 7shows the classified landslide susceptibility
map. The map shows the area of the basin consisting of Tb, Tek and Pzm deposits and that
steep slopes are the most hazardous. It is observed that the banks of the Sera River and its
tributaries are the most susceptible to landslides. Similar results are observed for the area
surrounding the basin.
5.3 Evaluation
Previous studies include statements about evaluating the performance of logistic regression
models: (1) the significant Wald statistic for independent variables should be less than 0.05
(Bai et al. 2010; Dahal et al. 2012); (2) the Nagelkerke
R2should be greater than 0.2 (Clark
and Hosking 1986; Ayalew and Yamagishi 2005); (3) AUC should be greater than 0.7
(Hosmer and Lemeshow 2000; Song et al. 2008); and (4) the Brier score should be less
than 0.25 (Steyerberg et al. 2010). Based on these criteria, the regression model generated
in this study showing
R2of 0.545, Brier score of 0.133 and Wald statistics of \0.05 for
most classes of predictors is considered satisfactory (Table 3). The percentages of correctly
Table 2 Landslide density (LD) for the classes of the landslide triggering parameters
Slope (°) LD Aspect LD Curvature LD
\10 0.253 Flat 0.001 Concave 1.493
10–20 1.168 North 0.661 Flat 0.078
20–30 0.974 East 1.043 Convex 0.747
30–40 0.920 South 0.136
[40 4.057 West 2.181
Relief (m) LD Lithology LD Distance to river (m) LD
\50 0.058 Pzm 0 \250 1.359
50–100 0.268 KTb 1.075832 250–500 1.814
100–150 0.223 Qal 0 500–1000 0.036
150–200 0.211 Tb 1.385608 1000–2000 0
[200 0.930 Tek 0 [2000 0
\2 0
2–4 0.485
4–5 0.905
5–6 1.280
6–8 1.869
[8 0
Nat Hazards
Author's personal copy
Table 3 Performance results and logistic regression coefficients of the model
Regression coefficient Standardised coefficient SE Wald v
(Intercept) -2.724 -6.622 0.096 -28.358 \0.001
Slope (°)
\10 -2.362 -6.622 0.070 -33.966 \0.001
10–20 -1.394 -1.647 0.060 -23.221 \0.001
20–30 0.076 0.211 0.052 1.459 0.145
30–40 -1.441 -3.617 0.042 -34.443 \0.001
[40 2.362 5.927 0.070 33.966 \0.001
Flat -7.685 -15.530 36.087 -0.213 0.831
North 2.498 4.674 0.110 22.631 \0.001
East -0.021 -0.0484 0.098 -0.217 0.828
South -1.986 -8.431 0.098 -20.330 \0.001
West 7.663 32.617 0.087 0.213 0.831
Concave 1.366 2.555 0.016 87.026 \0.001
Flat -0.294 -0.667 0.043 -6.879 \0.001
Convex -1.366 -3.100 0.016 -87.026 \0.001
\50 0.830 1.554 0.111 7.511 \0.001
50–100 -2.278 -5.172 0.104 -21.933 \0.001
100–150 -0.880 -3.734 0.099 -8.898 \0.001
150–200 -1.580 -4.431 0.100 -15.801 \0.001
[200 -0.830 -2.328 0.111 -7.511 \0.001
KTb -1.184 -1.399 0.024 -50.143 \0.001
Qal -8.188 -22.774 0.215 -38.048 \0.001
Tb 1.184 3.293 0.024 50.143 \0.001
Distance to river
\250 3.757 9.428 0.069 54.213 \0.001
250–500 5.503 11.120 0.067 82.321 \0.001
500–1000 -3.757 -7.592 0.069 -54.213 \0.001
1000–2000 NA NA NA NA NA
[2000 NA NA NA NA NA
2–4 -1.093 -3.065 0.048 -22.756 \0.001
4–5 -0.353 -0.417 0.018 -19.656 \0.001
5–6 0.215 0.599 0.021 10.111 \0.001
6–8 0.628 1.5764 0.062 10.102 \0.001
[8-11.235 -22.705 1054.439 -0.011 0.991
Nat Hazards
Author's personal copy
classified points were achieved for a cut-off value of 0.5 for the training and validation
samples. Table 5(classification accuracy results for the validation of the model) shows a
good, stable logistic regression model with an overall accuracy of 80.1 and 81.9 % for the
training and validation samples. Area under the ROC curves (Fig. 8) indicate that the
logistic regression model is highly accurate, for both the training and validation samples
generated high AUC values (89.3 and 83.0 %, respectively).
Therefore, the computed logistic regression model is representative of landslide activity
in the model area. The model can be used more widely to evaluate landslide susceptibility
in the Sera River Basin as the basin has similar geomorphological and geological char-
acteristics to the area under study.
6 Discussion
Areas with high susceptibility of landslides are found in close proximity to water courses.
Toe erosion and steep slopes near river banks lead to slope instability and thus to landslides
(Liu et al. 2004). Toe erosion, a main cause of landslides in river valleys refers to stream
flows that undercut banks, resulting in sloughing and prompting slope failures (Tamrakar
et al. 2014; Midgley et al. 2012). The Black Sea Region, including the Sera River Basin, is
dominated by broadleaf forests. The root systems of broad-leaf trees are extensive, a factor
that helps prevent landslides. However, along the rivers are settlements and arable land
(hazelnut farms) (Demir et al. 2015b), which has led to an increase in landslide occur-
rences, particularly where land has been cleared on the steep banks (Fig. 7) and roots and
other physical barriers have been removed (Pandey et al. 2007).
The steep slopes of the Sera River Basin may also be a factor in causing landslides.
Highly susceptible regions in this regard are mostly south of Lake Sera, where strata dip
uniformly in one direction and cause differential erosion. Similarly, the reason why the
western and northern banks of the Sera River are more susceptible to landslides as com-
pared to the eastern and southern banks may be due to the litho-structural characteristics of
the region. Slope influences the susceptibility of an area to landslides as well as the
magnitude of landslides (Grelle et al. 2011). The logistic regression model employed in
this study emphasised the importance of aspect and lithology, which leads to the con-
clusion that slope is a major factor in determining landslide activity in the Sera River
Basin. Rock lithologies such as sandstone, mudstone and claystone that have low shear
strength properties and thin beds are the most landslide prone in the Black Sea region
(Duman et al. 2005). In cataclinical slope areas where strata dip towards slope angle, such
as on the western and southern banks of the Sera River, slope instability and translational
slope failures and slumps are more likely (Liu et al. 2004; Grelle et al. 2011). Conversely,
Table 4 Upper threshold values
(TV), derived by Jenks’ method,
and percentages (%) of landslide
susceptibility classes from the
total area of the study region
Susceptibility class TV %
Very low 0.093 43.5
Low 0.280 17.7
Medium 0.491 11.5
High 0.709 13.4
Very high 0.999 13.9
Nat Hazards
Author's personal copy
when the dip of the bed goes against the slope angle (anaclinal slope areas), strata tend to
be more resistant to erosion and landslides.
Despite the positive results obtained, the landslide susceptibility model presented in this
study, as is the case of any statistical method, has some inherent limitations. These are: (1)
all landslides regardless of type were considered which resulted in a high degree of
generalisation; (2) being small scaled, the model does not consider the large spatial
variability of local conditions (especially geotechnical ones) which influence landslide
occurrence; (3) the model assumes that landslides will occur under the influence of the
Fig. 7 Landslide susceptibility map of the Sera River Basin
Table 5 Percentages of correctly classified points with respect to training and validation samples, using a
cut-off value of 0.5
Landslide-free points Landslide points Overall accuracy
Training sample 85.6 60.0 80.1
Validation sample 96.0 67.2 81.9
Nat Hazards
Author's personal copy
same combination of predictors. For a more complete model, variables such as the dip of
the bed/strata and vegetation cover could be included. The inclusion of more variables
would not necessarily mean the model performs better, as this depends on the quality of
data (Coe et al. 2000; Fabbri et al. 2003), but it would allow for testing and confirmation of
how vegetation cover and dip of the bed relate to landslide activity. In this regard, lack of
landslide records is a limiting factor. Despite the satisfactory results generated by the
logistic regression model, the sample size was limited and concentrated on one area of the
basin only. The expansion of the study area may allow for the inclusion of more landslide
data from the surrounding areas, thus producing a richer landslide inventory that may be
used for validation purposes. In addition, new methods are being developed for the
preparation of landslide inventory maps, e.g. Santangelo et al. (2015) present a semi-
automatic procedure using GIS for the digitalization of landslide obtained from aerial
photographs, reducing the subjectivity from manual visual transfer to the digital database.
Such methods may be used to improve the quality of the landslide inventory, although
high-resolution aerial photographs of the study area, which are currently unavailable, are
required for this purpose.
Landslide susceptibility values are not absolute but are relative (Fell et al. 2008).
However, even with limited data, the landslide susceptibility map is significant to policy-
makers as it allows the understanding of the increasing risk of landslide in the region. This
can help to prioritise funding for landslide risk mitigation measures at the municipal levels,
which is a preliminary stage for regional planning, and designing landslide risk mitigation
plans (Pellicani et al. 2014).
7 Conclusion
This research attempted to follow different steps in order to produce the landslide sus-
ceptibility using logistic regression model in a GIS environment. This helps to understand
the future landslide probability of the area and its spatial distribution, which is important in
terms of infrastructure development and land use management.
Fig. 8 ROC curves with
associated AUC values computed
from the training sample and the
validation sample
Nat Hazards
Author's personal copy
Landslides are widespread geohazards caused by geology, geomorphology, hydrology,
climate, land use and other factors. Most of the Trabzon province, in the Eastern Black Sea
Region of Turkey, is currently at risk from landslides, mostly as a result of poor land use
practice and deforestation. This includes the Sera River Basin. The Sera Lake, located in
the north of the basin, was formed as a result of a landslide in 1950, and since then there
have been further landslides in the region. Therefore, it is important to assess landslide
susceptibility in the area. Hazard mapping allows us to understand past and present
landslide activity and thus to determine the future risks. Landslide susceptibility refers to
the spatial occurrence probability of landslides and can be modelled to a relatively high
degree of accuracy by using a combination of statistical approaches and GIS.
Several approaches exist for modelling landslide susceptibility. A logistic regression
model was employed in this study. The logistic regression model generated different
probabilities for the occurrence of landslides by considering and assessing the conditions
that led to past and present slope failures and landslides. The parameters selected included
slope angle, aspect, lithology, TWI, proximity to rivers and relative relief. The model
satisfied the criteria set for evaluating its performance and was therefore deemed to rep-
resent accurately the relationships between the selected parameters and potential landslide
activity in the Sera River Basin. The landslide susceptibility maps showed that regions
along streams and south of the Sera Lake are highly vulnerable to landslides. This is
attributed to ‘‘soft’ lithologies, which have low resistance to erosion and landslide pro-
cesses, and slope instability as a result of toe erosion, which is shaped by the distance to
water courses.
Other important causative factors of landslides include the dip of the bed, land use, and
the type and extent of vegetation cover. However, these factors were not considered. Field
investigations and the production of detailed geological maps (including strata dip angle
and directions) were also beyond the scope of this study. The incomplete landslide
inventory map of the region poses a problem for landslide susceptibility mapping as the
current landslide activity is concentrated north of the lake, and the map reflects this. A
means to improve model performance could be to expand the study area and consider a
larger scale. However, this would require detailed landslide records, which are currently
not available. Nevertheless, given the positive results obtained in this study, it can be
concluded that logistic regression could be a significant means by which the landslide
susceptibility in the Black Sea region can be assessed.
Akgun A (2012) A comparison of landslide susceptibility maps produced by logistic regression, multi-
criteria decision, and likelihood ratio methods: a case study at Izmir, Turkey. Landslides 9:93–106
Akgun A, Bulut F (2007) GIS-based landslide susceptibility for Arsin-Yomra (Trabzon North Turkey)
region. Environ Geol 51:1377–1387
Akgun A, Kıncal C, Pradhan B (2011) Application of remote sensing data and GIS for landslide risk
assessment as an environmental threat to Izmir city (west Turkey). Environ Monit Assess
Alimohammadlou Y, Najafi A, Yalcin A (2013) Landslide process and impacts: a proposed classification
method. Catena 104:219–232
Alkhasawneh MS, Ngah UK, Tay LT, Isa NAM, Al-batah MS (2013) Determination of important topo-
graphic factors for landslide mapping analysis using MLP network. Sci World J 2013:1–12
Althuwaynee OF, Pradhan B, Park HJ, Lee HJ (2014) A novel ensemble bivariate statistical evidential belief
function with knowledge-based analytical hierarchy process and multivariate statistical logistic
regression for landslide susceptibility mapping. Catena 114:21–36
Nat Hazards
Author's personal copy
Armas I, Vartolomei F, Stroia F, Brasoveanu L (2013) Landslide susceptibility deterministic approach using
geographic information systems: application to Breaza town Romania. Nat Hazards 70:995–1017
Ayalew L, Yamagishi H (2005) The application of GIS-based logistic regression for landslide susceptibility
mapping in the Kakuda-Yahiko Mountains Central Japan. Geomorphology 65:15–31
Aydin A, Tecimen HB (2010) Temporal soil erosion risk evaluation: a CORINE methodology application at
Elmalıdam watershed Istanbul. Environ Earth Sci 61(7):1457–1465
Bai SB, Wang J, Lu
¨GN, Zhou PG, Hou SS, Xu SN (2010) GIS-based logistic regression for the landslide
susceptibility mapping of the Zhongxian segment in the three Gorgers area China. Geomorphology
Bayrak T, Ulukavak M (2009) Trabzon landslides. Electron J Mapp Technol 1:20–30
Beven K, Kirkby MJ (1979) A physically based variable contributing area model of basin hydrology. Hydrol
Sci Bull 24:43–69
Boztas C (1986) Limnological survey of the Sera Lake and reintroduction of fish project. Project Report No
1 Trabzon: Ministry of Agriculture and Rural Affairs of the Republic of Turkey Directorate of the
Trabzon Province
Brenning A, Gruber S, Hoelzle M (2005) Sampling and statistical analyses of BTS measurements. Permafr
Periglac Process 16:383–393
Brier GW (1950) Verification of forecasts expressed in terms of probability. Mon Weather Rev 78:1–3
Bui DT, Lofman O, Revhaug I, Dick OB (2011) Landslide susceptibility analysis in the Hoa Binh province
of Vietnam using statistical index and logistic regression. Nat Hazards 59:1413–1444
Bui DT, Lofman O, Revhaug I, Dick OB (2012) Spatial prediction of landslide hazards in Hoa Binh
province (Vietnam): a comparative assessment of the efficacy of evidential belief functions and fuzzy
logic models. Catena 96:28–40
Can T, Nefeslioglu HA, Gokceoglu C, Sonmez H, Duman TY (2005) Susceptibility assessments of shallow
earthflows triggered by heavy rainfall at three catchments by logistic regression analyses. Geomor-
phology 72:250–271
Cavalli M, Goldin B, Comiti F, Brardinoni F, Marchi L (2016) Assessment of erosion and deposition in
steep mountain basin by differencing sequential digital terrain models. Geomorphology. doi:10.1016/j.
Cavus A (2014) An touristic area requiring assessment in for nature tourism in the west of Trabzon: Sera
Lake. Turkish Geogr Rev 63:43–49
Chauhan S, Sharma M, Arora MK (2010) Landslide susceptibility zonation of the Chamoli region, Garhwal
Himalayas, using logistic regression model. Landslides 7:411–423
Clark WA, Hosking PL (1986) Statistical methods for geographers. Wiley, New York
Coe JA, Michael JA, Crovelli RA, Savage WZ (2000) Preliminary map showing landslide densities mean
recurrence intervals and exceedance probabilities as determined from historic records Seattle Wash-
ington USGS Open File Report 2000-303. http://www.pubsusgsgov/of/2000/ofr-00-0303/. Accessed 29
June 2015
Dahal RK, Hasegawa S, Bhandary NP, Poudel PP, Nonomura A, Yatabe R (2012) A replication of landslide
hazard mapping at catchment scale. Geo Nat Hazards Risk 3:161–192
Dai FC, Lee CF (2002) Landslides characteristics and slope instability modeling using GIS Lantau Island
Hong Kong. Geomorphology 42:213–228
Dai FC, Lee CF, Xu ZW (2001) Assessment of landslide susceptibility on the natural terrain of Lantau
Island Hong Kong. Environ Geol 40:381–391
De Vita P, Napolitano E, Godt JW, Baum RL (2013) Deterministic estimation of hydrological thresholds for
shallow landslide initiation and slope stability models: case study from the Somma-Vesuvius area of
southern Italy. Landslides 10:713–728
Demir G, Aytekin M, Akgun A (2015a) Landslide susceptibility mapping by frequency ratio and logistic
regression methods: an example from Niksar-Resadiye (Tokat Turkey). Arab J Geosci 8:1801–1812
Demir O, Inan HI, Cemal B, Uzun B (2015b) Land management for erosion prevention: a case study for a
Turkish nature reserve. Land Use Policy 47:394–400
Di Stefano C, Ferro V, Porto P, Tusa G (2000) Slope curvature influence on soil erosion and deposition
processes. Water Resour 36:607–617
Duman TY, Can T, Emre O, Kecer M, Dogan A, Ates S, Durmaz S (2005) Landslide inventory of
northwestern Anatolia. Turkey Eng Geol 77:99–114
Dunning SA, Mitchell WA, Rosser NJ, Petley DN (2007) The Hattian Bala rock avalanche and associated
landslides triggered by the Kashmir Earthquake of 8 October 2005. Eng Geol 93:130–144
Ercanoglu M, Temiz FA (2011) Application of logistic regression and fuzzy operators to landslide sus-
ceptibility assessment in Azdavay (Kastamonu, Turkey). Environ Earth Sci 64:949–964
Nat Hazards
Author's personal copy
Fabbri AG, Chung CF, Cendrero A, Remondo J (2003) Is prediction of future landslides possible with a
GIS? Nat Hazards 30:487–499
Fall M, Azzam R, Noubactep C (2006) A multi-method approach to study the stability of natural slopes and
landslide susceptibility mapping. Eng Geol 82:241–263
Fan X, van Westen CJ, Xu Q, Gorum T, Dai F, Wang G, Huang R (2013) Spatial distribution of landslide
dams triggered by the 2008 Wenchuan earthquake. In: Margottini C, Canuti P, Sassa K (eds) Landslide
science and practice, vol 5. Springer, London, pp 279–285
Fell R, Corominas J, Bonnard C, Cascini L, Leroi E, Savage WZ (2008) Guidelines for landslide suscep-
tibility, hazard and risk zoning for land-use planning. Eng Geol 102:99–111
Flach PA (2010) ROC analysis. In: Sammut C, Webb GI (eds) Encyclopedia of machine learning. Springer,
New York, pp 869–875
Flentje P, Chowdhury RN, Tobin P (2000) Management of landslides triggered by a major storm in
Wollongong, Australia. In: Proceeding of the II international conference on debris-flow hazards mit-
igation, mechanics, prediction and assessment, Taipei, pp 479–487
Galli M, Ardizzone F, Cardinali M, Guzzetti F, Reichenbach P (2008) Comparing landslide inventory maps.
Geomorphology 94:268–289
Ghosh S, Carranza EJM, van Westen CJ, Jetten VG, Bhattacharya DN (2011) Selecting and weighting
spatial predictors for empirical modeling of landslide susceptibility in the Darjeeling Himalayas (In-
dia). Geomorphology 131(1–2):35–56
Grelle G, Revellino P, Donnarumma A, Guadagno FM (2011) Bedding control on landslides: a method-
ological approach for computer-aided mapping analysis. Nat Hazard Earth Syst 11:1395–1409
Guzzetti F, Carrara A, Cardinali M, Reichenbach P (1992) Debris flows triggered by the July, 17–19, 1987
storm in the Valtellina Area (Northern Italy). In: Proceeding of the VII international congress inter-
praevent, Bern, vol 2, pp 193–204
Guzzetti F, Carrara A, Cardinali M, Reichenbach P (1999) Landslide hazard evaluation: an aid to a sus-
tainable development. Geomorphology 31:181–216
Guzzetti F, Reichenbach P, Ardizzone F, Cardinali M, Galli M (2006) Estimating the quality of landslide
susceptibility models. Geomorphology 81(1–2):166–184
Heckmann T, Gegg K, Gegg A, Becht M (2014) Sample size matters: investigating the effect of sample size
on a logistic regression susceptibility model for debris flows. Nat Hazards Earth Syst Sci 14:259–278
Herath S, Wang Y (2009) Case studies and national experiences. In: Sassa K, Canuti P (eds) Landslides–
disaster risk reduction. Springer, Berlin, pp 475–497. doi:10.1007/978-3-540-69970-5
Hina S, Kawasaki A, Qasim M (2014) Landslide susceptibility analysis using GIS and logistic regression
model: a case study in Malang, Indonesia. Asian J Environ Disaster Manag 6(2):117–129
Hosmer DW, Lemeshow S (2000) Applied logistic regression. Wiley, Chichester
Inan HI, Yomralioglu T, Ulger NE (2011) Evaluation of national farmer’s registry data in geoinformation
context: case study of Trabzon. Turkey Sci Res Essays 6:422–429
Irvem A, Topaloglu F, Uygur V (2007) Estimating spatial distribution of soil loss over Seyhan River Basin
in Turkey. J Hydrol 336:30–37
Jenks GF (1977) Optimal data classification for choropleth maps. University of Kansas
Jia N, Mitani Y, Xie M, Djamaluddin I (2012) Shallow landslide hazard assessment using a three-dimen-
sional deterministic model in a mountainous area. Comput Geotech 45:1–10
Kawasaki A, Hattori K, Urakawa G, Nakajima T, Sadohara S (2001) The utilization of GIS for the measure
against slope failure disaster. Theory Appl GIS 9(2):25–32
Kayastha P, Dhital MR, De Smedt F (2013) Application of the analytical hierarchy process (AHP) for
landslide susceptibility mapping: a case study from the Tinau watershed west Nepal. Comput Geosci
King G, Zeng L (2001) Logistic regression in rare events data. Polit Anal 9:137–163
Kjekstad O, Highland L (2009) Economic and social impacts of landslides. In: Sassa K, Canuti P (eds)
Landslides–disaster risk reduction. Springer, Berlin, pp 573–587. doi:10.1007/978-3-540-69970-5
Korup O, Clague JJ, Hermanns RL, Hewitt K, Strom AL, Weidinger JT (2007) Giant landslides topography
and erosion. Earth Planet Sci Lett 261:578–589
Korup O, Gorum T, Hayakawa Y (2012) Without power? Landslide inventories in the face of climate
change. Earth Surf Proc Land 37:92–99
Lee S (2005) Application of logistic regression model and its validation for landslide susceptibility mapping
using GIS and remote sensing data. Int J Remote Sens 26:1477–1491
Lee S, Min K (2001) Statistical analysis of landslide susceptibility at Yongin Korea. Environ Geol
Lee S, Sambath T (2006) Landslide susceptibility mapping in the Damrei Romel area, Cambodia using
frequency ratio and logistic regression models. Environ Geol 50:847–855
Nat Hazards
Author's personal copy
Liu JG, Mason PJ, Clerici N, Chen S, Davis A, Miao F, Deng H, Liang L (2004) Landslide hazard
assessment in the Three Gorges areas of the Yangtze river using ASTER imagery: Zigui-Badong.
Geomorphology 61:171–187
Mancini F, Ceppi C, Ritrovato G (2010) GIS and statistical analysis for landslide susceptibility mapping in
the Daunia area Italy. Nat Hazard Earth Syst 10:1851–1864
˘rint MC, Grozavu A, Patriche CV (2013) Assessing the spatial variability of coefficients of landslide
predictors in different regions of Romania using logistic regression. Nat Hazards Earth Syst Sci
Menard S (2002) Applied logistic regression analysis, 2nd edn. Sage Publications, Thousand Oaks
Meusburger K, Alewell C (2009) On the influence of temporal change on the validity of landslide sus-
ceptibility maps. Nat Hazards Earth Syst Sci 9:1495–1507
Midgley TL, Fox GA, Heeren DM (2012) Evaluation of the bank stability and toe erosion model (BSTEM)
for predicting lateral retreat on composite streambanks. Geomorphology 145–146:107–114
Moore DI, Grayson RB, Ladson AR (1991) Digital terrain modeling: a review of hydrological geomor-
phological and biological applications. Hydrol Process 5:3–30
Nagelkerke NJD (1991) A note of a general definition of the coefficient of determination. Biometrika
Nefeslioglu HA, Duman TY, Gokceoglu C (2008) Landslide susceptibility mapping for a part of tectonic
Kelkit Valley (Eastern Black Sea region of Turkey). Geomorphology 94:401–418
Notti D, Meisina C, Zucca F, Balduzzi G, Colombo A (2015) Map numerical modelling of landslides using data
from different monitoring systems: the example of Rosone (Western Alps). Eng Geol Soc Territ
Othman A, Gloaguen R (2013) River courses affected by landslides and implications for hazard assessment:
a high resolution remote sensing case study in NE Iraq-W Iran. Remote Sensing 5:1024–1044
Pandey A, Dabral PP, Chowdary VM, Yadav NK (2007) Landslide hazard zonation using remote sensing
and GIS: a case study of Dikrong river basin Arunachal Pradesh India. Eng Geol 54:1517–1529
Pellicani R, Van Westen CJ, Spilotro G (2014) Assessing landslide exposure in areas with limited landslide
information. Landslides 11:463–480
Pirasteh S, Woodbridge K, Rizvis SMA (2009) Geo-information technology (GIT) and tectonic signatures:
the River Karun and Dez, Zagros Orogen in south-west Iran. Int J Remote Sens 30:389–403
Pourghasemi HR, Mohammady M, Pradhan B (2012) Landslide susceptibility mapping using index of
entropy and conditional probability models in GIS: Safarood Basin Iran. Catena 97:71–84
Pradhan B (2011a) Manifestation of an advanced fuzzy logic model coupled with Geo-information tech-
niques to landslide susceptibility mapping and their comparison with logistic regression modelling.
Environ Ecol Stat 18:471–493
Pradhan B (2011b) Use of GIS-based fuzzy logic relations and its cross application to produce landslide
susceptibility maps in three test areas in Malaysia. Environ Earth Sci 63:329–349
Pradhan B (2013) A comparative study on the predictive ability of the decision tree support vector machine
and neuro-fuzzy models in landslide susceptibility mapping using GIS. Comput Geosci 51:350–365
Pradhan B, Lee S (2010) Landslide susceptibility assessment and factor effect analysis: backpropagation
artificial neural networks and their comparison with frequency ratio and bivariate logistic regression
modelling. Environ Model Softw 25(6):747–759
Raghuvanshi TK, Ibrahim J, Ayalew D (2014) Slope stability susceptibility evaluation parameter (SSEP)
rating scheme-an approach for landslide hazard zonation. J Afr Earth Sc 99:595–612
R Development Core Team (2015) The R project for statistical computing. http://www.r-projectorg/.
Accessed 21 June 2015
Reis S, Nisanci R, Yomralioglu T (2009) Designing and developing a province-based spatial database for
the analysis of potential environmental issues in Trabzon Turkey. Environ Eng Sci 26:123–130
Remondo J, Gonza
´ez A, De Tera
´n JRD, Cendrero A (2003) Landslide susceptibility models utilizing
spatial data analysis techniques. a case study from the lower Deba Valley, Guipu
´zcoa (Spain). Nat
Hazard 30:267–279
Santangelo M, Marchesini I, Bucci F, Cardinali M, Fiorucci F, Guzzetti F (2015) An approach to reduce
mapping errors in the production of landslide inventory maps. Nat Hazards Earth Syst Sci 15:2111–2126
Sarıyılmaz O (1972) Trabzon Regional geological study of landslides between ‘‘Akc¸aabat-Mac¸ka-Su
mene’’. Geology undergraduate thesis, Karadeniz Technical University
Sarkar S, Anbalagan R (2008) Landslide hazard zonation mapping and comparative analysis of hazard
zonation maps. J Mt Sci 5:232–240
Schicker R, Moon V (2012) Comparison of bivariate and multivariate statistical approaches in landslide
susceptibility mapping at a regional scale. Geomorphology 161–162:40–57
Nat Hazards
Author's personal copy
Schlogel R, Doubre C, Malet J, Masson F (2015) Landslide deformation monitoring with ALOS/PALSAR
imagery: a D-InSAR geomorphological interpretation method. Geomorphology 231:314–330
Shahabi H, Khezri S, Ahmad B, Allahvirdiasl H (2012) Application of satellite images and fuzzy set theory
in landslide hazard mapping in Central Zab Basin IOSR. J Appl Phys 1:17–24
Song R, Hiromo D, Kazutoki A, Usio K, Sumio M (2008) Modeling the potential distribution of shallow-
seated landslides using the weights of evidence method and a logistic regression model: a case study of
the Sabae Area Japan. Int J Sediment Res 23:106–118
Steyerberg EW, Vickers AJ, Cook NR, Gerds T, Gonen M, Obuchowski N, Pencina MJ, Kattan MW (2010)
Assessing the performance of prediction models: a framework for some traditional and novel measures.
Epidemiology 21:128–138
Suzen ML, Doyuran V (2004) Data driven bivariate landslide susceptibility assessment using geographical
information systems: a method and application to Asarsuyu catchment Turkey. Eng Geol 71:303–321
Swets JA (1988) Measuring the accuracy of diagnostic systems. Science 240(4857):1285–1293
Tamrakar NK, Bajracharya R, Sapkota S, Thapa I, Paudel P, Tamang NB (2014) Riverbank erosion
potential and channel stability status of the Kodku River southern Kathmandu Basin Central Nepal.
Bull Dep Geol 17:1–41
Tang C, Zhu J, Qi X, Ding J (2011) Landslides induced by the Wenchuan earthquake and the subsequent
strong rainfall event: a case study in the Beichuan area of China. Eng Geol 122:22–33
Timilsina M, Bhandary N, Dahal RK, Yatabe R (2014) Distribution probability of large-scale landslides in
Central Nepal. Geomorphology 226:236–248
Van Den Eeckhaut M, Marre A, Poesen J (2010) Comparison of two landslide susceptibility assessments in
the Champagne-Ardenne region (France). Geomorphology 115(1–2):41–155
Wu Y, Tang H, Yin K (2003) Application of matter-element model in landslide hazard risk assessment. Geol
Sci Technol Inf 22:96–100
Wu Y, Chen L, Cheng C, Yin K, Torok A (2014) GIS-based landslide hazard predicting system and its real-
time test during a typhoon Zhejiang Province Southeast China. Eng Geol 175:9–21
WWF (2015) The Caucasus Ecoregion. http://www.fpandaorg. Accessed 21 June 2015
Yalcin A (2007) Environmental impacts of landslides: a case study from East Black Sea Region Turkey.
Environ Eng Sci 24:821–833
Yalcin A (2008) GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate
statistics in Ardesen (Turkey): comparisons of results and confirmations. Catena 72:1–12
Yalcin A (2011) A geotechnical study on the landslides in the Trabzon Province NE Turkey. Appl Clay Sci
Yalcin A, Bulut F (2007) Landslide susceptibility mapping using GIS and digital photogrammetric tech-
niques: a case study from Adresen (NE-Turkey). Nat Hazards 41:201–226
Yalcin A, Kavurmaci MM (2013) Landsliding and flooding event triggered by heavy rains in the Rize
region. In: EGU Geophysical Research Abstracts vol 15, p 7063
Yalcin A, Reis S, Aydinoglu AC, Yomralioglu T (2011) A GIS-based comparative study of frequency ratio
analytical hierarchy process bivariate statistics and logistics regression methods for landslide sus-
ceptibility mapping in Trabzon NE Turkey. Catena 85(3):274–287
Yalcinkaya M, Bayrak T (2005) Comparison of static kinematic and dynamic geodetic deformation models
for Kutlugu
¨n landslide in Northeastern Turkey. Nat Hazards 34:91–110
Yesilnacar E, Topal T (2005) Landslide susceptibility mapping: a comparison of logistic regression and
neural networks methods in a medium scale study, Hendek region (Turkey). Eng Geol 79:251–266
Yilmaz I (2009) Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural
networks and their comparison: a case study from Kat landslides (Tokat-Turkey). Comp Geosci
Youssef AM, Pradhan B, Jebur MN, El-Harbi HM (2015) Landslide susceptibility mapping using ensemble
bivariate and multivariate statistical models in Fayfa area, Saudi Arabia.Environ Earth Sci 73:3745–3761
Zare M, Pourghasemi HR, Vafakhah M, Pradhan B (2013) Landslide susceptibility mapping at Vaz
Watershed (Iran) using an artificial neural network model: a comparison between multilayer perceptron
(MLP) and radial basic function (RBF) algorithms. Arab J Geosci 6:2873–2888
Zaruba Q, Mencl V (2014) Landslides and their controls, 2nd edn. Elsevier Science Publishing, New York
Zhu L, Huang J (2006) GIS-based logistic regression method for landslide susceptibility mapping in regional
scale. J Zhejiang Univ Sci A 7(12):2007–2017
Zhu A, Wang R, Qiao J, Qin C, Chen Y, Liu J, Du F, Lin Y, Zhu T (2014) An expert knowledge-based
approach to landslide susceptibility mapping using GIS and fuzzy logic. Geomorphology 214:128–138
Zhuang J, Peng J, Iqbal J, Liu T, Li Y, Ma P (2015) Identification of landslide spatial distribution and
susceptibility assessment in relation to topography in the Xi’an Region Shaanxi Province China. Front
Earth Sci 9:449–462
Nat Hazards
Author's personal copy
... LSM is an essential tool that incorporates potential landslide locations (Senouci et al., 2021). The probability of a landslide occurring in a particular region owing to the effects of several causative factors is referred to as landslide susceptibility (Reichenbach et al., 2018). LSM is an essential step towards landslide risk management and helps in effective mapping of the spatial distribution of probable landslide manifestations (Dai et al., 2002). ...
... In the past, researchers have used a range of models to assess landslide susceptibility using technologies such as Earth observation (EO) and a geographic information system (GIS). The recognition and analysis of slope movements have been going on since the early 1970s (Brabb et al., 1972) and is still one of the most important components in performing LSM (Ercanoglu and Gokceoglu, 2002;Chacón et al., 2006;Guzzetti et al., 2006;Castellanos Abella and Van Westen, 2008;Floris et al., 2011;Catani et al., 2013;Pham et al., 2015;Reichenbach et al., 2018;Youssef and Pourghasemi, 2021;Liu et al., 2021). ...
... Presently, two approaches -(1) statistical and (2) machine learning -are practised for LSM for investigating the landslide predisposing factors and for mapping the geographical distribution of landslide processes. Reichenbach et al. (2018) classified landslide susceptibility models into six main groups: (1) classical statistics, (2) index-based, (3) machine learning, (4) multi-criteria analysis, (5) neural networks, and (6) others. Research by Reichenbach et al. (2018) also depicted that before 1995, only 5 models were used for LSM, but in recent times, an investigation of 19 other models was carried out, which yielded good results. ...
Full-text available
In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important, as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (frequency ratio and evidence belief function) and two machine learning (ML) models (random forest and XGBoost; eXtreme Gradient Boosting) for LSM in the province of Belluno (region of Veneto, northeastern Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least “important” features by using a common threshold of 0.30 for statistical and 0.03 for ML algorithms. Conclusively, we found that removing the least important features does not impact the overall accuracy of LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least important ones, namely the aspect plan and profile curvature, topographic wetness index (TWI), topographic roughness index (TRI), and normalized difference vegetation index (NDVI) in the case of the statistical model and the plan and profile curvature, TWI, and topographic position index (TPI) for ML algorithms. This confirms that the requirement for the important conditioning factor maps can be assessed based on the physiography of the region.
... Relief amplitude refers to the difference between the altitude of the highest point and the altitude of the lowest point in a particular area and can effectively reflect the gravitational potential energy of terrain that is closely related to landslide occurrence [39]. In this study, the relief amplitude was reclassified into five classes: Gully density, defined as the channel length per unit area, represents an effective factor in LSM [1]. ...
... The SPI reflects the intensity of stream erosion on the surface and therefore influences the occurrence of landslides [39]. The SPI values were divided into six classes: <6, 6-12, 12-18, 18-24, 24-30, and >30 ( Figure 2(g)). ...
Full-text available
In the present study, a hybrid machine learning model was designed by integrating ant colony optimization (ACO), particle swarm optimization (PSO), and support vector machine (SVM) algorithms. The model was used to map the landslide susceptibility of the Anninghe Fault Zone in Sichuan Province, China. Based on this, 12 conditioning factors associated with landslides were considered, namely altitude, slope angle, cutting depth, slope aspect, relief amplitude, stream power index (SPI), gully density, lithology, rainfall, road density, distance to fault, and peak ground acceleration (PGA). The overall performance of the two resulting models was tested using the receiver operating characteristic (ROC), area under the ROC curve (AUC), Cohen’s kappa coefficient, and five statistical evaluation measures. The success rates of the ACO-PSO-SVM model and the SVM model were 0.898 and 0.814, respectively, while the prediction rates of the two models were 0.887 and 0.804, respectively. The results show that the ACO-PSO-SVM model yields better overall performance and accurate results than the SVM model. Therefore, in conclusion, the ACO-PSO-SVM model can be applied as a new promising method for landslide susceptibility mapping in subsequent studies. The results of this study will be useful for land-use planning, hazard prevention, and risk management.
... Globally, rock landslides cause approximately 300 deaths per year and a property damage of about 1 billion dollars (Zhan et al. 2019;Liao et al. 2019). According to Raja et al. (2017) and Zhang et al. (2020a, b, c, d), rock landslides account for 3% of all deaths caused by natural disasters. Hydraulic fracturing (HF) is a physical phenomenon of the initiation, propagation and penetration of micro fracture in rock under high water pressure until generate macro fracture and causes slope failure (Zhan and Cen 2007;Wang et al. 2020;Lyu et al. 2020). ...
Full-text available
Hydraulic fracturing (HF) is an important reason for inducing rock landslides. The impacts of the angle between the transverse pressure stress and the initial fracture, the transverse pressure stress, the length and aperture of the initial fracture on the critical water pressure stress of HF were analyzed based on the model tests of cement mortar specimens. The HF numerical simulations were carried out and the fracture aperture, pore pressure, strain and stiffness degradation index were analyzed, and the HF mechanism of rock was revealed. Taking a rock slope along G205 in China as an example, the landslide stability under high groundwater pressure was studied by numerical simulations, and the whole processes of the expansion, propagation, penetration and the rock slope failure were reproduced. The results showed that when HF occurred on the cement mortar specimens, a large amount of water seeped from the fracture and made a dull sound of failure, the water pressure on the fracture plane decreased rapidly, but not completely penetrated, and there was still a certain residual strength of the specimen. The HF of rock is a quasi-brittle failure, including static stage, micro fracture propagation stage and macro fracture formation stage. There are 3 dangerous rocks on the rock slope, among which WYT3 is in a stable state under the natural condition and in an unstable state under the rainstorm condition and seismic condition. The fracture propagation of WYT3 under the action of high groundwater pressure experienced slow development stage, rapid development stage and penetration stage, among which the slow development stage lasted the longest, and the slope failure occurred immediately after the fracture penetrated.
... have achieved higher AUC scores at 0.93, and 0.977(Micheletti et al. 2014;Song et al. 2018). The performance of the models in this case study is likely limited by the data, as ML model performance is limited by the quality and quantity of data supplied(Fabbri et al. 2003;Raja et al. 2017).The 19 input features were shown to have varying levels of importance in modelling landslide potential dependent on the regions used in each training-testing permutation. The in uence that each feature has on modelling landslide potential is location speci c, as the spatial distribution of certain geohazards varies. ...
Full-text available
Among natural hazards occurring offshore, submarine landslides pose a significant risk to offshore infrastructure installations attached to the seafloor. With the offshore being important for current and future energy production, there is a need to anticipate where future landslide events are likely to occur on the seafloor to support planning and development projects. Using the Gulf of Mexico (GoM) as a case study, this paper performs Landside Susceptibility Mapping (LSM) using a Gradient Boosted Decision Tree (GBDT) model to characterize the spatial patterns of submarine landslide probability over the U.S. Exclusive Economic Zone (EEZ) where water depths are greater than 120 meters. With known spatial extents of historic submarine landslides and a Geographic Information System (GIS) database of known topographical, geomorphological, geological, and geochemical factors, the resulting model was capable of accurately forecasting where the potential source location of sediment instability is more likely to occur. Results of a permutation modelling approach indicate that LSM accuracy is sensitive to training set size with accuracies becoming more stable as the number of observations increases. The influence that each input feature has on predicting landslide susceptibility was evaluated using the SHapely Additive exPlanations (SHAP) feature attribution method. Areas of high and very high susceptibility were associated with steep terrain including salt basins and escarpments. This case study serves as an initial assessment of the machine learning (ML) capabilities for producing accurate submarine landslide susceptibility maps given the current state of available natural hazard-related datasets and conveys both successes and limitations.
... In an area, the vicinity to a water body increases the probability of a slope failure by raising fluid pore pressure and slope toe erosion, that's why distance to drainage (Fig. 6a) is determined as a key influencing parameter in the slope failure [34,90]. The project area comprises a large drainage network because of the mountainous terrain which was extracted by using ALOPS PALAR DEM and further reclassify in Arc GIS 10.8. ...
Full-text available
The Himalayan region, a rugged mountain zone is among the most susceptible zones to the landslide hazard due to its terrain, geography, and active tectonics. Machine learning (ML) techniques are most advanced and precise methods to develop landslide susceptibility model (LSM). The current study was designed to analyze and assess the landslide susceptibility using ML approaches for District Hattian Bala, NW Himalayas, Pakistan. The historical satellite imageries are used to generate spatiotemporal landslide inventories of year 2005, 2007 and 2012. A spatial database was created pertaining to topographic, environmental, geologic, and anthropogenic factors including slope, aspect, elevation, curvature, plane curvature, profile curvature, topographic wetness index (TWI), lithology, distance to faults, distance to streams, distance to roads, normalized difference vegetation index (NDVI) and land use/ land cover (LULC). These LCFs were selected to analyze periodic landslide susceptibility in the region. The experimental design utilized 349, 393, and 735 landslide inventory of 2005, 2007, and 2012 respectively. Two ML models, i.e., Random Forest (RF) and Logistic Regression (LR) were applied to assess landslide susceptibility determine by thirteen landslide causative factors (LCFs). The spatiotemporal landslide inventory was partitioned into training (70%) and testing (30%) landslides for respective years to check the prediction accuracies of selected ML models. Comparative analysis of different LSMs was performed by the Receiver Operator Curves – Area Under Curves (ROC-AUC). The resultant accuracy, MAE, RMSE, Kappa, Precision, Recall, F1 indicated that RF outperformed the LR model. The study aims to minimize losses to lives and potential economic damage linked with recurrent slope instabilities in the region. It is anticipated that use of ML algorithms would support concerned authorities and organizations to effectively plan and manage landslide hazard in the region.
Based on a curved shield tunnel, this study classified the grades of segment cracking and damage during the construction and counted the segment cracking and damage. Combined with the data of tunnelling parameters, the significance of segment cracking and damage factors was analysed by the ordered multi-classification logistic regression method. Furthermore, the refined finite element numerical model was established to study the damage mechanism of the segment under the rolling angle. The results indicate that the analysis results of numerical simulation correspond to the field phenomena, which confirms that the rolling angle is a critical factor affecting the segment disease. The total stiffness of the segment attenuates significantly after torsion. When the torque is 43580.17 kN·m, the maximum longitudinal bolt stress connecting the segment out of the shield shell and the segment in the shield shell reaches 619.6 MPa, close to 640 MPa of the bolt yield stress.
Full-text available
Landslide disasters frequently occur along the highway G30 in the Guozigou Valley, the corridor of energy, material, economic and cultural exchange, etc., between Yili and other cities of China and Central Asia. However, little attention has been paid to assess the detailed landslide susceptibility of the strategically important highway, especially with high spatial resolution data and the generative presence-only MaxEnt model. Landslide susceptibility assessment (LSA) is a first and vital step for preventing and mitigating landslide hazards. The goal of the current study was to perform LSA for the landslide-prone highway G30 in Guozigou Valley, China with the aid of GIS tools and Chinese high resolution Gaofen-1 (GF-1) satellite data, and analyze and compare the performance of the maximum entropy (MaxEnt) model and logistic regression (LR). Thirty five landslides were determined in the study region, using GF-1 satellite data, official data, and field surveys. Seven landslide conditioning factors, including altitude, slope, aspect, gully density, lithology, faults density, and NDVI, were used to investigate their existing spatial relationships with landslide occurrences. The LR and MaxEnt model performance were assessed by the receiver operating characteristic curve, presenting areas under the curve equal to 0.85 and 0.94, respectively. The performance of the MaxEnt model was slightly better than that of the LR model. A landslide susceptibility map was created through reclassifying the landslides occurrence probability with the classification method of natural breaks. According to the MaxEnt model results, 3.29% and 3.82% of the study region is highly and very highly susceptible to future landslide events, respectively, with the highest landslide susceptibility along the highway. The generated landslide susceptibility map could help government agencies and decision-makers to make wise decisions for preventing or mitigating landslide hazards along the highway and design schemes of highway engineering and maintenance in Guozigou Valley, the mountainous areas.
Landslides caused countless economic and casualty losses in China, especially in mountainous and hilly areas. Landslide susceptibility mapping is an important approach and tool for landslide disaster prevention and control. This study presents a landslide susceptibility assessment using frequency ratio (FR) and index of entropy (IOE) models within a geographical information system for She County in the mountainous region of South Anhui, China. First, the landslide locations were ascertained in the study area using historical landslide records, aerial photographs, and multiple field surveys. In all, 502 landslides were identified and randomly divided into two groups as training (70%) and validation (30%) datasets. Additionally, the landslide-influencing factors, including slope angle, slope aspect, curvature, landform, lithology, distance to faults, distance to roads, distance to rivers, rainfall, and normalized difference vegetation index, were selected and their relative importance and weights were determined by FR and IOE models. The results show that the very high and high susceptibility classes cover nearly 50% of the study area. Finally, the comprehensive performance of the two models was validated and compared using receiver operating characteristic curves. The results demonstrated that the IOE model with the area under the curve (AUC) of 0.802, which is slightly better in prediction than the FR model (AUC = 0.786). The interpretation of the susceptibility map indicated that landform, slope degree, and distance to rivers plays a major role in landslide occurrence and distribution. The research results can be used for preliminary land use planning and hazard mitigation purposes.
Full-text available
This work evaluates the performance of three machine learning (ML) techniques, namely logistic regression (LGR), linear regression (LR), and support vector machines (SVM), and two multi-criteria decision-making (MCDM) techniques, namely analytical hierarchy process (AHP) and the technique for order of preference by similarity to ideal solution (TOPSIS), for mapping landslide susceptibility in the Chitral district, northern Pakistan. Moreover, we create landslide inventory maps from LANDSAT-8 satellite images through the change vector analysis (CVA) change detection method. The change detection yields more than 500 landslide spots. After some manual post-processing correction, the landslide inventory spots are randomly split into two sets with a 70/30 ratio for training and validating the performance of the ML techniques. Sixteen topographical, hydrological, and geological landslide-related factors of the study area are prepared as GIS layers. They are used to produce landslide susceptibility maps (LSMs) with weighted overlay techniques using different weights of landslide-related factors. The accuracy assessment shows that the ML techniques outperform the MCDM methods, while SVM yields the highest accuracy of 88% for the resulting LSM.
Full-text available
Landslide inventory maps (LIMs) show where landslides have occurred in an area, and provide information useful to different types of landslide studies, including susceptibility and hazard modelling and validation, risk assessment, erosion analyses, and to evaluate relationships between landslides and geological settings. Despite recent technological advancements, visual interpretation of aerial photographs (API) remains the most common method to prepare LIMs. In this work, we present a new semi-automatic procedure that exploits GIS technology for the digitalization of landslide data obtained through API. To test the procedure, and to compare it to a consolidated landslide mapping method, we prepared two LIMs starting from the same set of landslide API data, which were digitalized (a) manually adopting a consolidated visual transfer method, and (b) adopting our new semi-automatic procedure. Results indicate that the new semi-automatic procedure is more efficient and results in a more accurate LIM. With the new procedure, the landslide positional error decreases with increasing landslide size following a power-law. We expect that our work will help adopt standards for transferring landslide information from the aerial photographs to a digital landslide map, contributing to the production of accurate landslide maps.
Full-text available
Landslide dams are a common type of river disturbance in tectonically active mountain belts with narrow and steep valleys. Here we present an unprecedented inventory of 828 landslide dams triggered by the 2008 Wenchuan earthquake, China. Of the 828 landslide dams, 501 completely dammed the rivers, while the others only caused partial damming. The spatial distribution of landslide dams was similar to that of the total landslide distribution, with landslide dams being most abundant in the steep watersheds of the hanging wall of the Yingxiu-Beichuan Thrust Fault, and in the northeastern part of the strike-slip fault near Qingchuan. We analyzed the relation between landslide dam distribution and a series of seismic, topographic, geological, and hydrological factors.
Full-text available
Landslide inventory maps (LIMs) show where landslides have occurred in an area, and provide information useful to different types of landslide studies, including susceptibility and hazard modelling and validation, risk assessment, erosion analyses, and to evaluate relationships between landslides and geological settings. Despite recent technological advancements, visual interpretation of aerial photographs (API) remains the most common method to prepare LIMs. In this work, we present a new semi-automatic procedure that makes use of GIS technology for the digitization of landslide data obtained through API. To test the procedure, and to compare it to a consolidated landslide mapping method, we prepared two LIMs starting from the same set of landslide API data, which were digitized (a) manually adopting a consolidated visual transfer method, and (b) adopting our new semi-automatic procedure. Results indicate that the new semi-automatic procedure (a) increases the interpreter’s overall efficiency by a factor of 2, (b) reduces significantly the subjectivity introduced by the visual (manual) transfer of the landslide information to the digital database, resulting in more accurate LIMs. With the new procedure, the landslide positional error decreases with increasing landslide size, following a power-law. We expect that our work will help adopt standards for transferring landslide information from the aerial photographs to a digital landslide map, contributing to the production of accurate landslide maps.
Digital elevation models (DEMs) built from repeated topographic surveys permit producing DEM of Difference (DoD) that enables assessment of elevation variations and estimation of volumetric changes through time. In the framework of sediment transport studies, DEM differencing enables quantitative and spatially-distributed representation of erosion and deposition within the analyzed time window, at both the channel reach and the catchment scale. In this study, two high-resolution Digital Terrain Models (DTMs) derived from airborne LiDAR data (2. m resolution) acquired in 2005 and 2011 were used to characterize the topographic variations caused by sediment erosion, transport and deposition in two adjacent mountain basins (Gadria and Strimm, Vinschgau - Venosta valley, Eastern Alps, Italy). These catchments were chosen for their contrasting morphology and because they feature different types and intensity of sediment transfer processes. A method based on fuzzy logic, which takes into account spatially variable DTMs uncertainty, was used to derive the DoD of the study area. Volumes of erosion and deposition calculated from the DoD were then compared with post-event field surveys to test the consistency of two independent estimates. Results show an overall agreement between the estimates, with differences due to the intrinsic approximations of the two approaches. The consistency of DoD with post-event estimates encourages the integration of these two methods, whose combined application may permit to overcome the intrinsic limitations of the two estimations. The comparison between 2005 and 2011 DTMs allowed to investigate the relationships between topographic changes and geomorphometric parameters expressing the role of topography on sediment erosion and deposition (i.e., slope and contributing area) and describing the morphology influenced by debris flows and fluvial processes (i.e., curvature). Erosion and deposition relations in the slope-area space display substantial differences between the Gadria and the Strimm basins. While in the former erosion and deposition clusters are reasonably well discriminated, in the latter, characterized by a complex stepped structure, we observe substantial overlapping. Erosion mostly occurred in areas that show persistency of concavity or transformation from convex and flat to concave surfaces, whereas deposition prevailingly took place on convex morphologies. Less expected correspondences between curvature and topographic changes can be explained by the variable sediment transport processes, which are often characterized by alternation of erosion and deposition between different events and even during the same event.
Landslides continue to be a major natural disaster causing loss of life, extensive human suffering and economic losses, despite advances in understanding of mechanisms, monitoring and mitigation technologies related to landslides. Sharing the globally accumulated expertise and implementing this knowledge effectively in different local contexts is the major challenge now facing landslide loss reduction efforts. Landslides characteristics differ according to climatic, geological and geographical conditions. They are also affected by different triggering mechanisms depending on the livelihood practices, infrastructure development and population density in each locality. Landslide risk reduction practices and institutional arrangements have evolved in different countries in response to varied landslide experiences brought about by these different geo-physical characteristics and drivers. An objective analysis of the practices adopted worldwide would provide invaluable guidance to develop pragmatic landslide risk reduction strategies and responsible institutions, especially in the developing countries where the impacts are greatest and the vulnerabilities are the highest, especially with increasing hazard potential due to climate change. This chapter describes national programs and methodologies adopted in landslide risk reduction in various countries as a contribution in this direction
The Session, Socio-economic Impacts of Landslides, was organized to provide discussions on the socioeconomic impact of landslide events as well as best practice for mitigation of the risk associated with landslides. Social and economic losses, and their quantification, the consequences of landslides on infrastructure development, and land use policy, are critical aspects of socioeconomic issues related to landslides. In addition the session will include case studies on recovery and resettlement, measures to reduce social vulnerability, investments for landslide risk mitigation and reduction, and insurance issues for landslide risk mitigation and reduction.
Landslide inventory maps are effective and easily understandable products for both experts, such as geomorphologists, and for non experts, including decision-makers, planners, and civil defense managers. Landslide inventories are essential to understand the evolution of landscapes, and to ascertain landslide susceptibility and hazard. Despite landslide maps being compiled every year in the word at different scales, limited efforts are made to critically compare landslide maps prepared using different techniques or by different investigators. Based on the experience gained in 20 years of landslide mapping in Italy, and on the limited literature on landslide inventory assessment, we propose a general framework for the quantitative comparison of landslide inventory maps. To test the proposed framework we exploit three inventory maps. The first map is a reconnaissance landslide inventory prepared for the Umbria region, in central Italy. The second map is a detailed geomorphological landslide map, also prepared for the Umbria region. The third map is a multi-temporal landslide inventory compiled for the Collazzone area, in central Umbria. Results of the experiment allow for establishing how well the individual inventories describe the location, type and abundance of landslides, to what extent the landslide maps can be used to determine the frequency-area statistics of the slope failures, and the significance of the inventory maps as predictors of landslide susceptibility. We further use the results obtained in the Collazzone area to estimate the quality and completeness of the two regional landslide inventory maps, and to outline general advantages and limitations of the techniques used to complete the inventories.