Access to this full-text is provided by Taylor & Francis.
Content available from Geomatics, Natural Hazards and Risk
This content is subject to copyright. Terms and conditions apply.
Analysis of secondary-factor combinations of landslides
using improved association rule algorithms: a case study
of Kitakyushu in Japan
Jiaying Li
a,b
, Wei-Dong Wang
a,b
, Zheng Han
a
and Guangqi Chen
c
a
School of Civil Engineering, Central South University, Changsha, Hunan, China;
b
MOE Key
Laboratory of Engineering Structures of Heavy-haul Railway, Central South University, Changsha,
Hunan, China;
c
School of Engineering, Kyushu University, Fukuoka, Japan
ABSTRACT
Landslide analysis prevents landslides from threatening resident
safety and property, and the predominant method is susceptibility
assessment which is cumbersome and time-consuming. The asso-
ciation rule algorithm (ARA) is proposed to mine the correlation
between the factors and landslides simply and rapidly. The ori-
ginal ARA cannot reflect the scope of landslides which is non-
negligible for landslide analysis and is thus improved to mine the
frequent secondary-factor combinations (SFCs). Firstly, eight fac-
tors are selected using the out-of-bag error and chi-squared (v2)
test. The accuracy of the factor selection is further verified
employing landslide susceptibility assessment which is predicted
using 30% of study grid data selected randomly as the training
data. The improved ARA employs the area of historical landslides
to mine the frequent SFCs, and the results are then verified by
the frequency ratio and v2test. It is concluded that the frequent
SFCs are: (21, 41), (21, 74), (34, 41), (34, 74), (41, 74), (21, 41, 74),
and (34, 41, 74), and the area with the SFCs needs special protec-
tion. The present study provides a valuable reference for the pri-
mary prevention of landslides.
ARTICLE HISTORY
Received 1 December 2020
Accepted 21 June 2021
KEYWORDS
Landslide prevention; data
mining; improved ARA; SFC;
frequent combinations
1. Introduction
The occurrence of geo-hazards leads to casualties, property damage, and environmen-
tal issues (Wang et al. 2019; Li et al. 2021). The prediction and prevention of geo-
hazards is the focus of current scholars (Metternicht et al. 2005; Ma et al. 2019;Li
et al. 2020). However, geo-hazards, such as landslides, are difficult to predict accur-
ately even using current advanced technology due to complex natural and human fac-
tors, such as real-time rainfall and mining, and environmental compound elements,
such as geological condition and climatic condition. Analyzing and predicting
CONTACT Wei-Dong Wang 147745@163.com
ß2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/
licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
GEOMATICS, NATURAL HAZARDS AND RISK
2021, VOL. 12, NO. 1, 1885–1904
https://doi.org/10.1080/19475705.2021.1947904
landslides influenced by multi-factors is thus a difficult problem in scientific research
(Chen et al. 2020).
Anthropogenic activities, such as deforestation, engineering construction, and
improper land use, and natural environments, such as heavy rainfalls and earth-
quakes, result in slope instability and reshape the topography with complex dynamics
(Confuorto et al. 2017; Cebulski et al. 2020; Gomes et al. 2020). Nevertheless, the
importance of influencing factors is difficult to determine. The common methods are
field surveys and aerial photograph interpretation (Eker and Aydın2021).
Meanwhile, the machine learning algorithm (MLA) is an alternative method because
of the low cost and time cost (Sameen et al. 2020). It is broadly divided into super-
vised, unsupervised, and reinforcement learning (Leem and Kim 2020). In recent
years, MLA has been popularly used for biomedicine (Sung et al. 2020; Qin et al.
2021), software information technology (Gonz
alez et al. 2020; Singh and Singh 2020),
and ecological environment (Ge et al. 2020; Obsie et al. 2020; Wang, Zhou, et al.
2020). Currently, the landslide susceptibility assessment has been predicted using
MLA, such as support vector machine (SVM) (Hu et al. 2020; Saha and Saha 2020;
Wang, Feng, et al. 2020), deep learning algorithms (Bui et al. 2020; Dao et al. 2020),
artificial neural network ensemble (Bragagnolo et al. 2020; Fang et al. 2020), opti-
mized machine learning methods (Chen et al. 2020; Chen and Chen 2021), and opti-
mized intelligence models (Chen, Chen, Peng, et al. 2021; Chen and Li 2020; Zhao
and Chen 2020).
Hypothesis tests, such as chi-squared (v2) test, and statistical analysis methods are
proposed to select the significant factors (Pourghasemi, Kornejady, et al. 2020; Sahin
et al. 2020; Sameen et al. 2020; Wang, Kariminejad, et al. 2020). To date, the methods
have been successfully utilized in many study fields, namely text categorization (Yang
1997), credit risk assessments (Attigeri et al. 2017), and landslide susceptibility map-
ping (Sahin et al. 2020). The statistical analysis methods primarily include discrimin-
ant analysis (Dao et al. 2020), cluster analysis (Melchiorre et al. 2008), and
correlation analysis (Wistuba et al. 2021), etc. The statistical analysis methods com-
monly used for the selection of landslide-influencing factors are multicollinearity ana-
lysis (Du et al. 2020), accuracy analysis in the random forest (RF) model (Sun et al.
2020), and recursive feature elimination (Sun et al. 2020). Relevant literature proposes
various models for susceptibility assessment of landslides using the selected factors
(Pham et al. 2016; Huang and Zhao 2018). Although the assessment results are
refined and accurate, the process of assessment using conventional statistical methods
is laborious, cumbersome, and time-consuming. The methods are thus not convenient
enough to apply to the susceptibility assessment with excessive data and cumber-
some processes.
An alternative approach needs to be developed due to the limitation of susceptibil-
ity assessment of landslides. Researchers tend to pay attention to the factor combin-
ation prone to landslides (Pourghasemi, Kariminejad, et al. 2020; Yao et al. 2019),
which requires the methods to extract useful information from large amounts of data
quickly and accurately. Data mining is an effective method to extract knowledge from
complicated data (Ouyang et al. 2011; Witten et al. 2011; Sameen et al. 2020).
1886 J. LI ET AL.
Association rule algorithm (ARA) is an effective data mining algorithm to analyze the
landslide factors (Tsai et al. 2013).
ARA is a process of discovering associations among items or itemsets (Bagui et al.
2020). A classic algorithm for discovering frequent itemsets and association rules is
the Apriori algorithm which requires scanning the database multiple times (Agrawal
and Srikant 2000; Xie et al. 2019). It is applied in many research fields such as engin-
eering applications (Guo et al. 2014; Singh et al. 2018) and data management (Cheng
et al. 2015). The Frequent Pattern (FP)-Growth algorithm is another well-known
algorithm for discovering frequent itemsets in a concise form (Pei and Yin 1970) and
only scans the dataset twice without candidate itemsets (Bagui et al. 2020). Due to its
efficiency, it is applied widely to electric management (Wang and Cheng 2018) and
network detection (Hidayanto et al. 2017). The Eclat algorithm represents the vertical
database without traversing the database repeatedly (Zaki 2000). It helps understand
the associations between items and performs better to long patterns (Das et al. 2018).
It is applied to various studies, namely transport management (Zheng and Wang
2014; Das et al. 2018) and energy consumption (Liu et al. 2020).
Mining the deep information of landslides, namely the frequent secondary-factor
combinations (SFCs), using ARA is simpler and more rapid for the preliminary pre-
vention of landslides, and it also further analyzes the association between causative
factors and landslides. However, the original ARA is difficult to apply to landslide
analysis because it mines the frequent itemsets by counting the occurrence number of
landslides. It cannot reflect the scope of landslides which is a non-negligible param-
eter for analysis. The original ARA thus needs to be improved by learning from the
Figure 1. Flowchart of the methodology.
GEOMATICS, NATURAL HAZARDS AND RISK 1887
area of historical landslide to apply to the study issue. Few studies in the current lit-
erature have improved the original ARA.
In the present study, the influencing factors of landslides are selected using out-of-
bag (OOB) error and v2test. The receiver operating characteristic (ROC) curve is
used for the verification of susceptibility assessment of landslides obtained using the
RF model, deep belief network (DBN) model, and SVM model, which further verifies
the accuracy of factor selection. The Apriori algorithm, FP-Growth algorithm, and
Eclat algorithm are improved to mine the frequent SFCs. The association rules
between the SFCs with landslides are then verified using the frequency ratio (FR) and
v2test.
2. Methodologies
2.1. Methodological flow
The flowchart consisting of five main steps are as follows: (a) preparing the data of
influencing factors and historical landslides; (b) selecting the influencing factors and
determining their importance to establish a factor system; (c) evaluating the landslide
susceptibility using various models based on the selected factors and verifying the
assessment results to further prove the accuracy of the factor selection; (d) taking the
area of historical landslides as a parameter to optimize the original ARA and mining
the frequent SFC; (e) verifying the frequent SFCs. The methodologies in the present
study are executed and presented in Figure 1.
2.2. Selection of influencing factor
2.2.1. OOB error and v2test
The OOB error is an index of feature selection (Arora and Kaur 2020; Wang,
Kariminejad, et al. 2020). Not only can it be used to obtain the significance of fea-
tures, but also determine the optimal number of features. Another index of feature
selection is Gini importance, but it is difficult to determine the optimal number of
features using the index. The OOB is thus used to determine the importance of the
influencing factors and the optimal factor number in the present study.
It assumes that the total number of OOB data is Owhich is classified using the RF
classifier. The number of classification errors Xis obtained because of the known
classification of OOB data, and the OOB error is obtained using the ratio of Xto O:
In this study, the influencing factors are ranked according to their OOB scores
obtained using the RF algorithm, and the least important factors are eliminated based
on the recursive feature elimination. According to OOB errors of different factor sets
in the elimination process, the optimal factor set is selected as the factor system.
The v2test is a hypothesis testing method for variable classification based on the
chi-squared distribution. It is a well-established technique for measuring independ-
ence and determining whether the variables are related (Do
gan et al. 2021). It
assumes that the actual values are unrelated to theoretical values, and the v2can be
calculated by Eq. 1.
1888 J. LI ET AL.
v2¼XðATÞ2
T(1)
where Ais the actual value; and Tis the theoretical value.
2.2.2. Susceptibility assessment model
The RF model, DBN model, and SVM model have extensively been applied in suscep-
tibility assessment, and it provides a solid foundation for the assessment. In the pre-
sent study, the landslide region is set to 1, while the non-landslide region is set to 0.
30% of study data are selected randomly as the training data to predict the landslide
susceptibility of each grid in the study area. The ROC curve is a commonly used
method to verify the assessment results of landslide susceptibility (Chen, Lei, et al.
2021; Chen, Chen, Janizadeh, et al. 2021). In the present study, the landslide suscepti-
bility is thus evaluated using the three models, and the accuracies of the assessment
results are verified using the ROC curve. The more accurate the assessment results
are, the higher the accuracy of factor selection is. RF model is an advanced integrated
learning algorithm based on the ensemble of unpruned classification trees which are
created by bootstrap sampling and random feature selection, and the results are
obtained by a majority voting of the various classification tree (Xie et al. 2019).
DBN is an efficient unsupervised learning algorithm in deep learning and a prob-
abilistic generative model composed of restricted Boltzmann machines (RBM). RBM
consists of the visual layer and hidden layer. There is no connection between the neu-
rons in each layer. A DBN is structured by several RBMs. The hidden layer of the
previous RBM is the visual layer of the next RBM, while the output of the previous
RBM is the input of the next RBM.
SVM is performed by many kernels function, such as linear function, polynomial
function, and radial basis function (RBF). The main parameters are the penalty par-
ameter (c) and the kernel function parameter (g). In the present study, the RBF is
chosen as the kernel function, and the optimal cand gare found using the grid
method and cross-validation.
2.3. Improved association rule learning
Association rule learning is a common algorithm for discovering strong rules hidden
in a large database and is used for mining the frequent SFC of landslides in the
study area.
2.3.1. Original ARA
The dataset of the original ARA is fTID: itemsetgin which the TID is the thing iden-
tifier, and the itemset is the content of the TID. The two parameters are the data
basis to find the association rules and frequent itemsets. There are two sub-problems
in the original ARA: (a) finding out the frequent datasets whose supports are greater
than the specified minimum support, and (b) determining the strong association rule
based on frequent itemsets and the minimum confidence. The support and confi-
dence are obtained respectively by Eq. 2 and Eq. 3.
GEOMATICS, NATURAL HAZARDS AND RISK 1889
SupportðA,BÞ¼PðA&BÞ, (2)
Confidence A )B
ðÞ
¼PAjB
ðÞ
¼PðA&BÞ
PðAÞ, (3)
where PðA&BÞis the probability of A and B concurrently; PðAjBÞdenotes the prob-
ability of B given A; and PðAÞis the probability of A.
Apriori algorithm is an ARA for Boolean mining based on a recursive algorithm
based on the two key steps, namely connection step pruning (Wang et al. 2018). The
FP-Growth algorithm compresses the data of frequent itemsets to a frequent pattern
tree and retains the itemset association information. There is no need for the candi-
date set and only a need to traverses the database twice. The Eclat algorithm is a
depth-first-search algorithm based on the set intersection. It is applied to sequential
and parallel issues with the characteristic of local reinforcement. Its inverted theory
considers the item and transaction ID as the key and value, respectively. The detailed
steps of the Apriori algorithm, FP-Growth algorithm, and Eclat algorithm are pro-
posed as Figure 2.
The original ARA mines the itemsets meeting the requirements of support and
confidence from a considerable amount of itemsets by counting the number of items.
Figure 2. Steps of Apriori algorithm, FP-Growth algorithm, and Eclat algorithm.
1890 J. LI ET AL.
It only can mine frequent SFCs by using the occurrence number of landslides and is
difficult to apply to the present study.
2.3.2. Improved ARA
In the present study, the scope of landslides is a non-negligible parameter for associ-
ation rule analysis. However, the two parameters of the original ARA cannot accur-
ately reflect the parameter. The characteristic is introduced, and the improved ARA
mines the frequent itemsets based on fTID: itemset, characteristicgin which the
characteristic is a continuous variable. The frequent itemsets are mined based on the
accumulation of the corresponding characteristic rather than the occurrence number
of the itemsets.
The characteristic, namely the area of historical landslides in this paper, is intro-
duced in the improved ARA. The support and confidence are optimized using the
area of historical landslides (Eqs. 4,5).
Support A,B
ðÞ
¼Area A&B
ðÞ
PArea , (4)
Confidence A )B
ðÞ
¼SupportðA,BÞ
Area A
ðÞ
=PArea ¼Area A&B
ðÞ
Area A
ðÞ , (5)
in which Area A&B
ðÞ
is the area of historical landslides with the secondary-factor A
and B;Area A
ðÞ
is the area of historical landslides with the secondary-factor A;and
PArea is the area of historical landslides.
For the improved Apriori algorithm, after the datasets are scanned, the candidate
itemsets are generated by accumulating the landslide area. The frequent SFC is mined
and then connected and pruned based on the support in Eq. 4. The confidence used
to generate rule is renewed using Eq. 5. For the FP-Growth algorithm, the root nodes
created in the frequent item table also include the characteristic accumulation, when
building the FP-Trees. For the Eclat algorithm, the support is calculated based on the
characteristic accumulation rather than the length of the TID set, and there is the
same improvement in the prior theory as the Apriori algorithm when the candidate
itemsets are generated.
On the other hand, the FR is used to prove the association between the frequent
SFCs obtained using improved ARA and landslides, and FR is obtained by Eq. 6.
FR ¼PðLFiÞ
PðFiÞ¼ALFi=AFi
AL=A¼ALFiA
AFiAL
, (6)
where ALFiis the area of historical landslide with the SFC Fi;AFiis the area with SFC
Fi;ALis the area of landslides; and Ais the area of the study area.
GEOMATICS, NATURAL HAZARDS AND RISK 1891
3. Data collection and preparation
3.1. Study area
Kitakyushu is located in the northern Kyushu Island, Japan (Figure 3). It indicates
the north latitude range of 33580–33430and the east longitude range of 130400-
131010, with an area of 488.78 km
2
. The terrain tilts from north to south with a rela-
tive altitude of 954 m. According to the geological characteristics and terrain genesis
of the study area, it can be mainly divided into four regions, namely the southern
mountain region, central plain region, northeastern mountain region, and northwest-
ern hilly region. The terrain is smooth and characterized by the overburden soil layer
thickness of about 1.30-1.76 m. According to the Ministry of Land, Infrastructure,
Transport and Tourism of Japan, the geological condition of the study area is com-
plex with an active geological tectonic movement. The geological formations are
mainly sedimentary rock and igneous rocks, and the landfill area is more than 5% of
the study area.
The study area is warm and humid throughout the year with an average annual
temperature of 16.2 C and average annual precipitation of 1265 mm (Sun et al.
2011). In the northern Kitakyushu, the area has a typical Sea of Japan climate, while
the climate in the eastern region belongs to the Seto Inland Sea Climate which is
warm and dry. The precipitation significantly varies, concentrated during the rainy
season and typhoon season. Meanwhile, the study area is located in the Pacific Rim
Volcanic Seismic Zone at the junction of Eurasian and Pacific plates with frequent
crustal movement. There are thus frequently occurring landslides induced by rainfall
and earthquake, and most of the landslides are shallow landslides with a sliding sur-
face depth of less than 6 m. The data of historical landslides is obtained from the
Figure 3. Location of the study area: (a) Fukuoka in Japan; (b) Kitakyushu in Fukuoka; and (c) his-
torical landslide area in the study area.
1892 J. LI ET AL.
Figure 4. Maps of the various factors.
GEOMATICS, NATURAL HAZARDS AND RISK 1893
Bureau of Land Policy in the Ministry of Land, Infrastructure, Transport and
Tourism of Japan, and the geological environment of landslide-prone regions is com-
plex, with active geological tectonic movements such as earthquakes. The historical
landslides from 1992 to 2011 are shown in Figure 3.
3.2. Case influencing factors
Landslides are typical multi-factor complex geo-hazards, and their mechanisms are
complicated with various induced factors. The Kitakyushu is considered as the study
area, and the data in the study area is obtained using the field environment and
related literature. The digital elevation model (DEM) data at a resolution of 10 m are
provided by the Geospatial Information Authority of Japan. The geology conditions,
such as lithology, surface information, and runoff, are provided by the Land and
Water Resources Bureau in the Ministry of Land, Infrastructure, Transport and
Tourism of Japan. The present study establishes a factor system consisting of ten fac-
tors, namely soil thickness (ST), cumulative runoff (CR), distance from road (DRO),
topography, elevation, distance from construction line (DCL), slope, distance from
railway (DRA), lithology, and distance from river (DRI). There are two qualitative
factors and eight quantitative factors in the established factor system. The factors in
Figure 5. Importance of factors in the various factor selections based on the recursive feature
elimination.
1894 J. LI ET AL.
the present study are divided into four levels to avoid too many factor levels leading
to the excessively great computational amount, and there are 40 secondary-factors.
Four quantitative factors, namely the ST, CR, elevation, and slope, are reclassified
using the natural break method. However, four additional quantitative factors, namely
the DRO, DCL, DRA, and DRI, are unsuitable to be reclassified by the same method
because the factors cannot affect the entire study area and their impacts disappear
beyond a short distance from them. Therefore, the four factors are reclassified within
a certain distance according to the actual influence scope of the factors. The maps of
the various factors are thus shown in Figure 4.
4. Results
4.1. Selection and verification of influencing factor
A significant characteristic of the RF model is the OOB which can calculate the fea-
ture importance. Based on the recursive feature elimination, the factor importance,
namely the OOB score, in the various factor selections and the OOB errors of various
factor selection are presented respectively in Figure 5 and Figure 6.
As shown in Figure 5 and Figure 6, the OOB error of eight influencing factors is
minimum, and the factors selected in the present study are thus DCL, topography,
DRO, slope, DRI, ST, CR, and DRA.
The v2test can be used to verify the significance of factors affecting landslides,
and the v2of the eight factors are obtained in Table 1 using Statistical Product and
Service Solutions (SPSS) and compared with the test critical value. The eight v2are
greater than the critical value (k ¼3.84) which proves the accuracy of factor selection.
4.2. Landslide susceptibility assessment
The landslide susceptibility assessment is employed to further verify the accuracy of
factor selection. The assessment results of landslide susceptibility are obtained using
the RF model, DBN model, and SVM model. The results are then classified using the
Figure 6. OOB errors of various factor selection.
GEOMATICS, NATURAL HAZARDS AND RISK 1895
natural breakpoint method into five levels, namely very low susceptibility, low suscep-
tibility, medium susceptibility, high susceptibility, and very high susceptibility, and
the level maps are obtained using the three models in Figure 7. The ROC curves of
the assessment results using the three models are obtained employing the historical
landslide data as a reference to verify the accuracy (Figure 8).
As can be seen from Figure 7, the level distributions of landslide susceptibility
maps obtained by the three models are very similar. The high-susceptibility areas are
mainly distributed in the south-central region, while the low-susceptibility areas are
distributed in the northern region. The area under the curve (AUC) is in the range
of 0.5-1, and an AUC of 1 indicates perfect prediction, while an AUC of 0.5 indicates
useless prediction. The AUCs of the RF model, DBN model, and SVM model are
respectively 0.909, 0.878, 0.809. The three AUCs of the three models are greater than
0.8, and it indicates that the performance of assessment results is excellent and results
in high accuracy. The highest accuracy is recorded by the RF model, followed by the
DBN model and SVM model. It can be concluded that the RF model has better
accuracy than the other models. Meanwhile, the results further prove the accuracy of
the factor selection.
4.3. Mining and verification of the frequent SFC
The secondary-factors of the study area are coded and shown in Table 2.
The improved ARA is executed in Python, and two parameters, namely the min-
imum support and confidence need to be set in the algorithm. Two methods are usu-
ally applied, namely the trial and error method and using other parameters to replace
the parameters (Zhang et al. 2017). However, the substitute parameter still needs to
be set if using the second method, and the issue is not fundamentally addressed. The
former approach is thus employed in the present study. The minimum support and
confidence are selected respectively as 60% and 70% using the trial and error method,
Table 1. v2of the selected factors.
Factors DCL Topography DRO Slope DRI ST CR DRA
v2135.9 3326.7 285.1 332.6 392.5 1484.5 446.9 997.5
Figure 7. Level maps of landslide susceptibility assessment using (a) RF model; (b) DBN model;
and (c) SVM model.
1896 J. LI ET AL.
and the two parameters are applied to the improved ARA. The frequent SFCs are
obtained as follows: (21, 41), (21, 74), (34, 41), (34, 74), (41, 74), (21, 41, 74) and (34,
41, 74). The average confidences of the frequent SFCs are shown in Table 3.
Meanwhile, the FR and v2are used to verified the association between the frequent
SFCs and landslides and are presented in Table 4.
Figure 8. ROC curve of the RF model, DBN model, and SVM model.
Table 2. Coding of various secondary-factors.
Factor Secondary-factor Coding Factor Secondary-factor Coding
ST (m) <1.54 11 CR (mm) <921
1.54–1.63 12 9–25 22
1.64–1.71 13 26–110 23
>1.71 14 >110 24
DRO (m) <20 31 Topography Mountain 41
20–50 32 Hill 42
51–100 33 Platform 43
>100 34 Plain 44
DCL (m) <100 51 Slope ()<861
100–200 52 8–20 62
201–400 53 21–35 63
>400 54 >35 64
DRA (m) <100 71 DRI(m) <200 81
100–200 72 200–400 82
201–400 73 401–800 83
>400 74 >800 84
Table 3. Confidences of the frequent SFCs.
Combination Confidence
(21, 41) 88.20%
(21, 74) 84.89%
(34, 41) 85.54%
(34, 74) 82.64%
(41, 74) 92.78%
(21, 41, 74) 88.89%
(34, 41, 74) 88.20%
GEOMATICS, NATURAL HAZARDS AND RISK 1897
The greater the FR is, the greater the probability of landslides is. As can be seen
from the table above, the FRs are greater than one, and it indicates the frequent SFCs
are prone to landslides. The SFCs are thus sorted: (34, 41), (34, 41, 74), (21, 41, 74),
(21, 41), (41, 74), (34, 74), and (21, 74). The v2is greater than the critical value,
which denotes that the frequent SFCs are prone to landslides. The SFCs are sorted
according to the v2:(34, 41), (41, 74), (34, 41, 74), (21, 41), (21, 41, 74), (34, 74),
and (21, 74). All FRs and v2are correspondingly greater than one and critical value,
which indicates a tight relationship between the SFCs and landslides. The most fre-
quent SFC is (34, 41), namely the distance from road >100 m and the topography
of the mountain, and the area with the frequent SFCs needs special protection.
4.4. Comparison with original ARA
The dataset of the original ARA is fTID: itemsetg, and the number of itemsets is the
number of historical landslides. The TID is the identifier of the landslides, and the
itemset is the secondary-factor with the largest area in the corresponding landslide.
However, there is no combination meeting the requirement of the minimum support
of improved ARA in the original ARA. The minimum support is thus set to 20%
using the trial and error method, while the minimum confidence is set to 40%. As a
result, there are three SFCs, namely (21, 41); (21, 74); and (41, 74), and their confi-
dences are 48.59%; 41.90%; and 50.70%, respectively.
It is concluded that even if the minimum support is set to 20%, the maximum
confidences of the three SFCs are only about 50%. It denotes that the results of data
mining by taking the number of landslides as the research objectives are inaccurate
enough for the study area, and the improved ARA is more applied to the study area
than the original ARA.
5. Discussions
According to the relevant literature (Xie et al. 2019), the geo-hazards including land-
slides are analyzed using the data statistics and research reports. However, much of
the literature on the analysis of geo-hazards pays particular attention to susceptibility
assessment. The MLAs, such as the RF model and SVM model, are the most com-
monly used approach (Chang et al. 2019; Merghadi et al. 2020). In recent years, deep
learning algorithms, such as the DBN model, begin to outperform previous traditional
methods and develop rapidly (Dou et al. 2020; Wang, He, et al. 2020). The models
have been the focus of studies on landslide prevention. Although the susceptibility
Table 4. FR and v2of the frequent SFCs.
Combination FR v2
(21, 41) 5.20 37.00
(21, 74) 3.71 4.29
(34, 41) 5.97 46.80
(34, 74) 4.95 22.99
(41, 74) 5.16 43.88
(21, 41, 74) 5.23 30.97
(34, 41, 74) 5.91 39.81
1898 J. LI ET AL.
assessment results are refined and accurate, the process of assessment is laborious,
cumbersome, and time-consuming. An alternative approach thus needs to be devel-
oped. Mining the deep information of the landslides using the data mining algorithm
is simpler and more rapid and also valuable for the preliminary prevention
of landslides.
Current studies have investigated the triggering factors and threshold analysis of
landslides employing the data mining methods and generated the association rules
between triggering factors and deformation (Ma et al. 2017; Miao et al. 2021).
Meanwhile, researchers have determined the cause-and-effect relationships between
factors and landslide movement by identifying the contribution of each parameter to
landslides employing association rule mining (Ma et al. 2017). However, the original
ARA only can be used for discrete problems, and the problems involving the continu-
ous variable cannot be solved. The method of the previous studies cannot apply to
this study because it cannot accurately reflect the scope of landslides which is a non-
negligible parameter, and few current studies have improved the original ARA. The
present study thus introduces the area of historical landslides to improve the original
ARA to apply to the analysis of landslide factors.
The landslide information can be mined by employing the improved association
rule analysis. Finding the frequent SFCs and discovering the association rules between
the landslides and the influencing factors are particularly useful for landslide preven-
tion. It provides a novel insight into the improvement of the ARA and a valuable ref-
erence for the primary prevention of landslides. However, the proposed method
mines the association rules based on the scope of landslides, and it thus only
addresses the issue in terms of space and has certain spatiotemporal limitations.
Future research should concentrate on the investigation of extracting more valuable
landslide information that optimizes the analysis of landslide prevention and rescue.
6. Conclusions
In the present study, the ARAs, namely the Apriori algorithm, FP-growth algorithm,
and Eclat algorithm, are improved for mining the frequent SFCs of landslides. There
are few studies on optimizing ARA in the same method and employing the improved
ARA to landslide analysis. The conclusions are obtained as follows:
1. The influencing factors of landslides in the study area are selected using the
OOB error and v2test. The factors are considered as the evaluation indices to
evaluate the landslide susceptibility using the RF model, DBN model, and SVM
model, which further verifies the accuracy of the factor selection.
2. The ARA is improved by introducing a continuous variable, namely the area of
historical landslides, to apply to the present study, and the frequent SFCs are
mined. It is proved that the frequent SFCs are: (21, 41), (21, 74), (34, 41), (34,
74), (41, 74), (21, 41, 74), and (34, 41, 74), and the association between the SFCs
and landslides is verified using their FRs and v2test. Their FRs are correspond-
ing 5.20, 3.71, 5.97, 4.95, 5.16, 5.23, and 5.91, and their v2are corresponding
GEOMATICS, NATURAL HAZARDS AND RISK 1899
37.00, 4.29, 46.80, 22.99, 43.88, 30.97, and 39.81 which are all greater than the
critical value.
3. The SFCs are sorted according to the FRs: (34, 41), (34, 41, 74), (21, 41, 74), (21,
41), (41, 74), (34, 74), and (21, 74), and they are also sorted according to v2:
(34, 41), (41, 74), (34, 41, 74), (21, 41), (21, 41, 74), (34, 74), and (21, 74). The
most frequent SFC is (34, 41), namely the distance from road >100 m and the
topography of the mountain, and the area with the frequent SFCs needs spe-
cial protection.
4. The results obtained employing the original ARAs are inaccurate enough for the
study area, and the improved ARA has more widespread applicability than the
original ARA. The improved ARA provides a valuable reference for the primary
prevention of landslides.
Disclosure statement
There are no financial competing interests.
Funding
This work was supported by the National Natural Science Foundation of China under Grant
No. 51478483 and No. 41702310 and the China Scholarship Council.
Data availability statement
The data that support the findings of this study are available from the corresponding authors,
upon reasonable request.
References
Agrawal R, Srikant R. 2000. Fast algorithms for mining association rules. In: Proceedings of
the 20th International Conference Very Large Data Bases (VLDB), 1215. Available from:
https://rakesh.agrawal-family.com/papers/vldb94apriori.pdf.
Arora N, Kaur PD. 2020. A Bolasso based consistent feature selection enabled random forest
classification algorithm: an application to credit risk assessment. Appl Soft Comput. 86:
105936.
Attigeri G, Pai M, Pai R. 2017. Credit risk assessment using machine learning algorithms. Adv
Sci Lett. 23(4):3649–3653.
Bagui S, Devulapalli K, Coffey J. 2020. A heuristic approach for load balancing the FP-growth
algorithm on MapReduce. Array. 7:100035.
Bragagnolo L, Silva RVd, Grzybowski JMV. 2020. Artificial neural network ensembles applied
to the mapping of landslide susceptibility. CATENA. 184:104240.
Bui DT, Tsangaratos P, Nguyen V-T, Liem NV, Trinh PT. 2020. Comparing the prediction
performance of a Deep Learning Neural Network model with conventional machine learn-
ing models in landslide susceptibility assessment. CATENA. 188:104426.
Cebulski J, Pasierb B, Wieczorek D, Zieli
nski A. 2020. Reconstruction of landslide movements
using digital elevation model and electrical resistivity tomography analysis in the Polish
outer carpathians. CATENA. 195:104758.
1900 J. LI ET AL.
Chang K-T, Merghadi A, Yunus AP, Pham BT, Dou J. 2019. Evaluating scale effects of topo-
graphic variables in landslide susceptibility models using GIS-based machine learning tech-
niques. Sci Rep. 9(1):12296.
Chen X, Chen W. 2021. GIS-based landslide susceptibility assessment using optimized hybrid
machine learning methods. CATENA. 196:104833. https://doi.org/10.1080/10106049.2021.
1892212
Chen Y, Chen W, Janizadeh S, Bhunia GS, Bera A, Pham QB, Linh NTT, Balogun A-L, Wang
X. 2021. Deep learning and boosting framework for piping erosion susceptibility modeling:
spatial evaluation of agricultural areas in the semi-arid region. Geocarto Int. 1–27.
Chen W, Chen X, Peng J, Panahi M, Lee S. 2021. Landslide susceptibility modeling based on
ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer. Geosci
Front. 12(1):93–107.
Chen W, Chen Y, Tsangaratos P, Ilia I, Wang X. 2020. Combining evolutionary algorithms
and machine learning models in landslide susceptibility assessments. Remote Sensing.
12(23):3854.
Chen W, Lei X, Chakrabortty R, Chandra Pal S, Sahana M, Janizadeh S. 2021. Evaluation of
different boosting ensemble machine learning models and novel deep learning and boosting
framework for head-cut gully erosion susceptibility. J Environ Manage. 284:112015.
Chen W, Li Y. 2020. GIS-based evaluation of landslide susceptibility using hybrid computa-
tional intelligence models. CATENA. 195:104777.
Cheng X, Su S, Xu S, Li Z. 2015. DP-Apriori: a differentially private frequent itemset mining
algorithm based on transaction splitting. Comput Secur. 50:74–90.
Confuorto P, Di Martire D, Centolanza G, Iglesias R, Mallorqui JJ, Novellino A, Plank S,
Ramondini M, Thuro K, Calcaterra D. 2017. Post-failure evolution analysis of a rainfall-trig-
gered landslide by multi-temporal interferometry SAR approaches integrated with geotech-
nical analysis. Remote Sens Environ. 188:51–72.
Dao DV, Jaafari A, Bayat M, Mafi-Gholami D, Qi C, Moayedi H, Phong TV, Ly H-B, Le T-T,
Trinh PT, et al. 2020. A spatially explicit deep learning neural network model for the pre-
diction of landslide susceptibility. CATENA. 188:104451.
Das S, Dutta A, Jalayer M, Bibeka A, Wu L. 2018. Factors influencing the patterns of wrong-
way driving crashes on freeway exit ramps and median crossovers: Exploration using ‘Eclat’
association rules to promote safety. Int J Transp Sci Technol . 7(2):114–123.
Do
gan O, Tas¸pınar S, Bera AK. 2021. A Bayesian robust chi-squared test for testing simple
hypotheses. Journal of Econometrics. 222(2):933–958.
Dou J, Yunus AP, Merghadi A, Shirzadi A, Nguyen H, Hussain Y, Avtar R, Chen Y, Pham
BT, Yamagishi H. 2020. Different sampling strategies for predicting landslide susceptibilities
are deemed less consequential with deep learning. Sci Total Environ. 720:137320.
Du J, Glade T, Woldai T, Chai B, Zeng B. 2020. Landslide susceptibility assessment based on
an incomplete landslide inventory in the Jilong Valley, Tibet, Chinese Himalayas. Eng Geol.
270:105572.
Eker R, Aydın A. 2021. Long-term retrospective investigation of a large, deep-seated, and
slow-moving landslide using InSAR time series, historical aerial photographs, and UAV
data: The case of Devrek landslide (NW Turkey). CATENA. 196:104895.
Fang Z, Wang Y, Peng L, Hong H. 2020. Integration of convolutional neural network and con-
ventional machine learning classifiers for landslide susceptibility mapping. Comput Geosci.
139:104470.
Ge G, Shi Z, Zhu Y, Yang X, Hao Y. 2020. Land use/cover classification in an arid desert-oasis
mosaic landscape of China using remote sensed imagery: performance assessment of four
machine learning algorithms. Global Ecol Conserv. 22:e00971.
Gomes PIA, Aththanayake U, Deng W, Li A, Zhao W, Jayathilaka T. 2020. Ecological frag-
mentation two years after a major landslide: correlations between vegetation indices and
geo-environmental factors. Ecol Eng. 153:105914.
GEOMATICS, NATURAL HAZARDS AND RISK 1901
Gonz
alez S, Garc
ıa S, Del Ser J, Rokach L, Herrera F. 2020. A practical tutorial on bagging
and boosting based ensembles for machine learning: algorithms, software tools, performance
study, practical perspectives and opportunities. Informat Fusion. 64:205–237.
Guo Z, Chi D, Wu J, Zhang W. 2014. A new wind speed forecasting strategy based on the
chaotic time series modelling technique and the Apriori algorithm. Energy Convers Manage.
84:140–151.
Hidayanto BC, Muhammad RF, Kusumawardani RP, Syafaat A. 2017. Network intrusion
detection systems analysis using frequent item set mining algorithm FP-max and Apriori.
Procedia Comput Sci. 124:751–758.
Hu Q, Zhou Y, Wang S, Wang F. 2020. Machine learning and fractal theory models for land-
slide susceptibility mapping: case study from the Jinsha River Basin. Geomorphology. 351:
106975.
Huang Y, Zhao L. 2018. Review on landslide susceptibility mapping using support vector
machines. CATENA. 165:520–529.
Leem J, Kim H. 2020. Action-specialized expert ensemble trading system with extended dis-
crete action space using deep reinforcement learning. Plos One. 15(7):e0236178.
Li J, Wang W, Han Z. 2021. A variable weight combination model for prediction on landslide
displacement using AR model, LSTM model, and SVM model: a case study of the Xinming
landslide in China. Environ Earth Sci. 80(10):386.
Li J, Wang W, Han Z, Li Y, Chen G. 2020. Exploring the impact of multitemporal DEM data
on the susceptibility mapping of landslides. Applied Sciences. 10(7):2518.
Liu Y, Hu X, Luo X, Zhou Y, Wang D, Farah S. 2020. Identifying the most significant input
parameters for predicting district heating load using an association rule algorithm. J Cleaner
Prod. 275:122984.
Ma R, Cui C, Ma M, Chen A. 2019. Performance-based design of bridge structures under
vehicle-induced fire accidents: basic framework and a case study. Eng Struct. 197:109390.
Ma J, Tang H, Hu X, Bobet A, Zhang M, Zhu T, Song Y, Ez Eldin MAM. 2017. Identification
of causal factors for the Majiagou landslide using modern data mining methods. Landslides.
14(1):311–322.
Melchiorre C, Matteucci M, Azzoni A, Zanchi A. 2008. Artificial neural networks and cluster
analysis in landslide susceptibility zonation. Geomorphology. 94(3–4):379–400.
Merghadi A, Yunus AP, Dou J, Whiteley J, ThaiPham B, Bui DT, Avtar R, Abderrahmane B.
2020. Machine learning methods for landslide susceptibility studies: a comparative overview
of algorithm performance. Earth Sci Rev. 207:103225.
Metternicht G, Hurni L, Gogu R. 2005. Remote sensing of landslides: an analysis of the poten-
tial contribution to geo-spatial systems for hazard assessment in mountainous environments.
Remote Sens Environ. 98(2–3):284–303.
Miao F, Wu Y, Li L, Liao K, Xue Y. 2021. Triggering factors and threshold analysis of baish-
uihe landslide based on the data mining methods. Nat Hazards. 105(3):2677–2696.
Obsie EY, Qu H, Drummond F. 2020. Wild blueberry yield prediction using a combination of
computer simulation and machine learning algorithms. Comput Electron Agric. 178:105778.
Ouyang Y, Luo SM, Cui LH, Wang Q, Zhang JE. 2011. Estimation of real-time N load in sur-
face water using dynamic data-driven application system. Ecol Eng. 37(4):616–621.
Pei J, Yin Y. 1970. Mining frequent patterns without candidate generation. Available from:
http://www.cse.msu.edu/cse960/Papers/MineFeqPatteren-HPY-SIGMOD2000.pdf.
Pham BT, Pradhan B, Tien Bui D, Prakash I, Dholakia MB. 2016. A comparative study of dif-
ferent machine learning methods for landslide susceptibility assessment: a case study of
Uttarakhand area (India). Environ Model Software. 84:240–250.
Pourghasemi HR, Kariminejad N, Gayen A, Komac M. 2020. Statistical functions used for spa-
tial modelling due to assessment of landslide distribution and landscape-interaction factors
in Iran. Geosci Front. 11(4):1257–1269.
Pourghasemi HR, Kornejady A, Kerle N, Shabani F. 2020. Investigating the effects of different
landslide positioning techniques, landslide partitioning approaches, and presence-absence
balances on landslide susceptibility mapping. CATENA. 187:104364.
1902 J. LI ET AL.
Qin X, Liu M, Zhang L, Liu G. 2021. Structural protein fold recognition based on secondary
structure and evolutionary information using machine learning algorithms. Comput Biol
Chem. 91:107456.
Saha A, Saha S. 2020. Comparing the efficiency of weight of evidence, support vector machine
and their ensemble approaches in landslide susceptibility modelling: a study on Kurseong
region of Darjeeling Himalaya, India. Remote Sens Appl: Soc Environ. 19:100323.
Sahin EK, Colkesen I, Acmali SS, Akgun A, Aydinoglu AC. 2020. Developing comprehensive
geocomputation tools for landslide susceptibility mapping: LSM tool pack. Comput Geosci.
144:104592.
Sameen MI, Sarkar R, Pradhan B, Drukpa D, Alamri AM, Park H-J. 2020. Landslide spatial
modelling using unsupervised factor optimisation and regularised greedy forests. Comput
Geosci. 134:104336.
Singh S, Garg R, Mishra PK. 2018. Performance optimization of MapReduce-based Apriori
algorithm on Hadoop cluster. Comput Electr Eng. 67:348–364.
Singh J, Singh J. 2020. Detection of malicious software by analyzing the behavioral artifacts
using machine learning algorithms. Inf Softw Technol. 121:106273.
Sun J, Wang L., Long P., Chen G. 2011. An assessment method for reginal susceptibility of
landslides under coupling condition of earthquake and rainfall. Chinese Journal of Rock
Mechanics and Engineering. 30(4):752–760.
Sun D, Wen H, Wang D, Xu J. 2020. A random forest model of landslide susceptibility map-
ping based on hyperparameter optimization using Bayes algorithm. Geomorphology. 362:
107201.
Sung SM, Kang YJ, Cho HJ, Kim NR, Lee SM, Choi BK, Cho G. 2020. Prediction of early
neurological deterioration in acute minor ischemic stroke by machine learning algorithms.
Clin Neurol Neurosurg. 195:105892.
Tsai F, Lai J-S, Chen WW, Lin T-H. 2013. Analysis of topographic and vegetative factors with
data mining for landslide verification. Ecol Eng. 61:669–677.
Wang J, Cheng Z. 2018. FP-growth based regular behaviors auditing in electric management
information system. Procedia Comput Sci. 139:275–279.
Wang Y, Feng L, Li S, Ren F, Du Q. 2020. A hybrid model considering spatial heterogeneity
for landslide susceptibility mapping in Zhejiang Province, China. CATENA. 188:104425.
Wang W, He Z, Han Z, Li Y, Dou J, Huang J. 2020. Mapping the susceptibility to landslides
based on the deep belief network: a case study in Sichuan Province. Nat Hazards. 103(3):
3239–3261.
Wang W, Li J, Qu X, Han Z, Liu P. 2019. Prediction on landslide displacement using a new
combination model: a case study of Qinglong landslide in China. Nat Hazards. 96(3):
1121–1139.
Wang C, Pan Y, Chen J, Ouyang Y, Rao J, Jiang Q. 2020a. Indicator element selection and
geochemical anomaly mapping using recursive feature elimination and random forest meth-
ods in the Jingdezhen region of Jiangxi Province, South China. Appl Geochem. 122:104760.
Wang X, Song C, Xiong W, Lv X. 2018. Evaluation of flotation working condition recognition
based on an improved Apriori algorithm. IFAC-PapersOnLine. 51(21):129–134.
Wang J, Zhou Y, Xiao F. 2020. Identification of multi-element geochemical anomalies using
unsupervised machine learning algorithms: a case study from Ag–Pb–Zn deposits in north-
western Zhejiang, China. Appl Geochem. 120:104679.
Wistuba M, Malik I, Gorczyca E,
SleRzak A. 2021. Establishing regimes of landslide activity –
Analysis of landslide triggers over the previous seven decades (Western Carpathians,
Poland). CATENA. 196:104888.
Witten IH, Frank E, Hall MA, 2011. Chapter 6 - Implementations: real machine learning
schemes. In: Witten IH, Frank E, Hall MA, editors. Data mining: practical machine learning
tools and techniques. 3rd ed. Boston: Morgan Kaufmann; p. 191–304.
Xie X, Fu G, Xue Y, Zhao Z, Chen P, Lu B, Jiang S. 2019. Risk prediction and factors risk ana-
lysis based on IFOA-GRNN and apriori algorithms: application of artificial intelligence in
accident prevention. Process Safe Environment Protect. 122:169–184.
GEOMATICS, NATURAL HAZARDS AND RISK 1903
Yang Y. 1997. A comparative study on feature selection in text categorization. In: Proceedings
of the 14th International Conference on Machine Learning (ICML’97); p. 412–420.
Yao W, Li C, Zuo Q, Zhan H, Criss RE. 2019. Spatiotemporal deformation characteristics and
triggering factors of Baijiabao landslide in Three Gorges Reservoir region, China.
Geomorphology. 343:34–47.
Zaki MJ. 2000. Scalable algorithms for association mining. IEEE Trans Knowl Data Eng. 12(3):
372–390.
Zhang Z, Pedrycz W, Huang J. 2017. Efficient frequent itemsets mining through sampling and
information granulation. Eng Appl Artif Intell. 65:119–136.
Zhao X, Chen W. 2020. Optimization of computational intelligence models for landslide sus-
ceptibility evaluation. Remote Sensing. 12(14):2180.
Zheng X, Wang S. 2014. Study on the method of road transport management information
data mining based on pruning Eclat algorithm and mapreduce. Proc Social Behav Sci. 138:
757–766.
1904 J. LI ET AL.
Available via license: CC BY 4.0
Content may be subject to copyright.
