ArticlePDF Available

Abstract and Figures

Salinity intrusion is a complex issue in coastal and estuarine areas. Currently, remote sensing techniques have been widely used to monitor water quality changes, ranging from inland river networks to deep oceans. The Vietnamese Mekong Delta is an important rice-growing area, and intrusion of saline water into irrigated freshwater-based agriculture areas is one of the most crucial constraints for agriculture development. This study aimed at building a numerical model to realize the salinity intrusion through the relationship between reflectance from the Landsat-8 Operational Land Imager images and salinity levels measured in situ. A total of 103 observed samples were divided into 50% training and 50% test. Multiple Linear Regression, Decision Trees and Random Forest (RF) approaches were applied in the study. The result showed that the RF approach was the best model to estimate salinity along the coastal river network in the study area. However, the large samples size needed was a significant challenge to circumscribe predicting ability of the RF model. The reflectance has a good correlation with salinity when locations (latitude–longitude) of salinity measured stations were added as a parameter of the Step-wise model with R-square 77.48% in training and 74.16% in test while Root Mean Square Error was smaller than 3.
Content may be subject to copyright.
Full Terms & Conditions of access and use can be found at
https://www.tandfonline.com/action/journalInformation?journalCode=tres20
International Journal of Remote Sensing
ISSN: 0143-1161 (Print) 1366-5901 (Online) Journal homepage: https://www.tandfonline.com/loi/tres20
Remote sensing techniques to predict salinity
intrusion: application for a data-poor area of the
coastal Mekong Delta, Vietnam
Phuong T.B Nguyen, Werapong Koedsin, Donald McNeil & Tri P.D Van
To cite this article: Phuong T.B Nguyen, Werapong Koedsin, Donald McNeil & Tri P.D Van (2018)
Remote sensing techniques to predict salinity intrusion: application for a data-poor area of the
coastal Mekong Delta, Vietnam, International Journal of Remote Sensing, 39:20, 6676-6691, DOI:
10.1080/01431161.2018.1466071
To link to this article: https://doi.org/10.1080/01431161.2018.1466071
Published online: 26 Apr 2018.
Submit your article to this journal
Article views: 232
View Crossmark data
Remote sensing techniques to predict salinity intrusion:
application for a data-poor area of the coastal Mekong Delta,
Vietnam
Phuong T.B Nguyen
a
, Werapong Koedsin
a
, Donald McNeil
b
and Tri P.D Van
c
a
Remote Sensing & Geo-Spatial Science Research Unit, Faculty of Technology and Environment, Prince of
Songkla University, Phuket, Thailand;
b
Department of Statistics, Macquarie University, Sydney, New South
Wales, Australia;
c
Department of Water Resources, Can Tho University, Can Tho, Vietnam
ABSTRACT
Salinity intrusion is a complex issue in coastal and estuarine areas.
Currently, remote sensing techniques have been widely used to
monitor water quality changes, ranging from inland river networks
to deep oceans. The Vietnamese Mekong Delta is an important
rice-growing area, and intrusion of saline water into irrigated
freshwater-based agriculture areas is one of the most crucial con-
straints for agriculture development. This study aimed at building
a numerical model to realize the salinity intrusion through the
relationship between reectance from the Landsat-8 Operational
Land Imager images and salinity levels measured in situ. A total of
103 observed samples were divided into 50% training and 50%
test. Multiple Linear Regression, Decision Trees and Random Forest
(RF) approaches were applied in the study. The result showed that
the RF approach was the best model to estimate salinity along the
coastal river network in the study area. However, the large sam-
ples size needed was a signicant challenge to circumscribe pre-
dicting ability of the RF model. The reectance has a good
correlation with salinity when locations (latitudelongitude) of
salinity measured stations were added as a parameter of the
Step-wise model with R-square 77.48% in training and 74.16% in
test while Root Mean Square Error was smaller than 3.
ARTICLE HISTORY
Received 29 July 2017
Accepted 5 April 2018
1. Introduction
Saline intrusion is a dicult issue for freshwater supply in coastal areas (Trung et al. 2016;Himi
et al. 2017). Extraordinary saline and short-term salinity intrusion can cause huge damages but
are hard to detect, on the short and long timescale, and it acts as a slow-onset hazard
(Consultative Group on International Agricultural Research CGIAR Research Centers in
Southeast Asia 2016;Binh2015). Much damage is done before the intrusion has been
identied. In the Vietnamese Mekong Delta (VMD), the salinity intrusion trend has historically
increased in terms of concentration and duration, leading to great threats to sustainable
freshwater-based agriculture development (Trung et al. 2016;Binh2015). Agricultural
CONTACT Werapong Koedsin werapong.g@phuket.psu.ac.th Remote Sensing & Geo-Spatial Science Research
Unit, Faculty of Technology and Environment, Prince of Songkla University, Phuket, Thailand
INTERNATIONAL JOURNAL OF REMOTE SENSING
2018, VOL. 39, NO. 20, 66766691
https://doi.org/10.1080/01431161.2018.1466071
© 2018 Informa UK Limited, trading as Taylor & Francis Group
enterprises including paddy rice, fruit, vegetable and freshwater-based aquaculture are the
most vulnerable due to the lack of any alternative freshwater supplies. However, the lack of
agility in providing salinity information from manager to local people is a critical problem:
farmers are not able to keep in touch with current information on salinity (CGIAR Research
Centers in Southeast Asia 2016). Increasing uncertainties and complexities exacerbated by
climate change and abnormal weather guarantee accurate information for salinity forecasting
will become more dicult (CGIAR Research Centers in Southeast Asia 2016).
Salinity intrusion is a complex process depending on many factors in the VMD. These
include freshwater discharge from upstream, capacity and morphology of the channel,
conguration of the drainage network, tidal conditions and the presence of control structures
such as sluice gates (Hashimoto 2001;Nguyenetal.2008). The magnitude of oods, summer
autumn paddy production growing-stage and rainfall frequency and magnitude (Deltares,
Delta Alliance and Federation of Water Resources Planning and Investigation in the South,
Vietnam 2011) in combination with impacts of sea level rise also exacerbate the damage of
salinity intrusion. Ability to predict salinity intrusion was an issue of interest in previous studies.
Even though hydraulic models were considered to be successfully developed to simulate
salinity intrusion in the VMD (Khang et al. 2008; Trung and Tri 2014), they are highly complex
requiring large input data (e.g. detailed topographical information and the latest knowledge
about the infrastructure), which is in many cases not achievable in remote areas (Nguyen et al.
2008). Meanwhile, remote sensing techniques open new potential applications to monitor
freshwater resource, salinity in coastal area and ocean salinity (Wang and Xu 2012). The
resolution applications of available satellite imgaes are particularly suited to coastlines and
estuaries (Roy et al. 2014).Thesuccessofsatelliteimagesfordetecting salinity intrusion was
demonstrated in dierent previous studies using the Landsat Thematic Mapper (Landsat TM;
Wang and Xu 2008; Baban 1997), the Moderate Resolution Imaging Spectroradiometer
(MODIS;Urquhartetal.2012), the Earth Observing-1 (EO-1 ALI; Fang et al. 2010), the Sea-
viewing Wide Field-of-view Sensor (Sea WiFS; DSa et al. 2002) and recently by the Landsat-8
Operational Land Imager (OLI; Zhao, Temimi, and Ghedira 2017). However, none of these
studies were done in a tropical monsoon location.
Remote sensing may relate suspended solids and coloured dissolved organic matters
from the river discharge to salinity and water reectance (Wang and Xu 2008). Thus,
salinity tends to precipitate Total Suspended Solids (TSS) and so has a good negative
correlation with salinity (Fang et al. 2010). Modelling salinity also was performed using
only single wavelength reectance remote sensing (Urquhart et al. 2012; Zhao, Temimi,
and Ghedira 2017). On the other hand, it was found that the location was the most
signicant predictor variable in surface salinity estimation models (Urquhart et al. 2012).
However, the locality issue is a major consideration when using the model for other
study areas that contains complex processing, freshwater inow and seasonality.
Machine learning has been successfully applied for dierent studies in the remote sensing
eld (Waske et al. 2009; Dev et al. 2016). Eight statistic models including a Categorical and
Regression Tree model (CART), a Generalized Linear Model (GLM), a Generalized Additive
Model (GAM), a Random Forest (RF) Model, a Mean model, an Articial Neural Network (ANN),
a Multivariate Adaptive Regression Spline (MARS) and a Bayesian Additive Regression Tree
(BART) were applied to nd out the best model for predicted salinity concentration in
Chesapeake Bay, in the United States (Urquhart et al. 2012). In another study, an ordinary
least square regression was performed to determine relationships between salinity and
INTERNATIONAL JOURNAL OF REMOTE SENSING 6677
reectanceinLakePontchartrain,intheUSGulfofMexico(WangandXu2008). A multi-
variable linear algorithm was employed for predicting sea surface salinity from remote sensing
reectance in the hypersaline Arabian Gulf (Zhao, Temimi, and Ghedira 2017). Choosing a
suitable model for detecting salinity depends on the characteristics of each study area.
However, lack of in situ data for supervised modelling is one of the great challenges in the
way of developing realistic applications of salinity modelling (Urquhart et al. 2012; Zhou and
Zhang 2016). Small sample size is related to overtting which causes serious limitations in
developing a useful model (Liu and Gillies 2016; Shcheglovitova and Anderson 2013). In such
cases, the model does good tting on the small number of training data points available but
would not do well in predicting for a new task on new samples (Ratner 2011).
This study sought to identify risk of salinity intrusion and develop a model using
reectance data from Landsat-8 OLI as a new approach to predict salinity in the
VMD. Two objectives of the study were: (i) to determine the most useful reectance
wavelength of the Landsat-8 OLI images and choosing a suitable statistic model to
predict salinity intrusion with the limited salinity observations available; and (ii) to
examine trends of saline intrusion by combining wavelength and location factors.
2. Methodology
2.1. Study area
The VMD, located in the downstream of the Mekong River, is at and low-lying area of highly
complex rivers and channels (Noh et al. 2013). The Tien River is one of the biggest
distributary river systems in the VMD. Before entering the East Sea, the Tien River splits
into four branches including the Cua Tieu, Cua Dai, Ham Luong and Co ChienCung Hau
(Figure 1). At a distance of 30 km from the South China Sea, the Co Chien River again splits
into two estuary branches: Co ChienCung Hau (Nguyen and Savenije 2006).
Figure 1. The study area and sampling locations of 17 salinity stations in Cua Dai, Cua Tieu, Ham
Luong and Co ChienCung Hau River.
6678 P. T. B. NGUYEN ET AL.
Annually, declining discharge from the upstream from the onset of the dry
season, strong wind speed from the sea and high tide level cause incursions of
saltwater along the rivers up to about 4050 km inland. Furthermore, the propor-
tion of discharge entering the delta river has signicant roles to determine salinity
distribution (both in terms of time and magnitude) in the dierent branches. In
2005, the discharge contribution at Cua Tieu was about 10% of total discharge in
the Tien River while the discharge in Cua Dai and Ham Luong were about 20.8%
and 10.2%, respectively. In the Co Chien river, the Co Chien estuary received 10.5%
and Cung Hau received 3.3%, and the remainder of the discharge was through
other parts of the delta (Nguyen et al. 2008). Thus, about 55% of the total Mekong
discharge occurs through the study area. In the VMD, the standard salinity alert
value is 4 parts per thousand (ppt), equivalent to about 12% of seawater (Deltares,
Delta Alliance and Federation of Water Resources Planning and Investigation in the
South, Vietnam 2011).
2.2. Data collection
2.2.1. Landsat-8 OLI collecting and processing
The Landsat-8 OLI has an entire Earth coverage every 16 days and 30 m × 30 m of
spatial resolution. Twenty-ve satellite images were used consisting of mostly cloud-
free scenes in the dry season (JanuaryJune) from 2013 to 2016. Scenes of images
were between 124/53 and 125/53 paths/rows. These images were used to extract
reectance data for a single pixel that also has data on salinity measured in the eld
at the time. Ground truthfrom 17 salinity stations was applied in the Region of
Interest (ROI) function in ENVI to identify 103 samples from these images.
First, radiometric correction was performed to normalize satellite images for
factorssuchassensordegradation,Earth-Sun distance variation, incidence angle,
view angle and time of data gathering were applied to the image data. This process
involved converting Digital Number (DN) into radiance using calibration parameters
that accompanied with the images metadata. The image was then atmospherically
corrected and transformed to reectance using the Moderate Resolution
Atmospheric Transmission-based Fast Line-of-sight Atmospheric Analysis of
Spectral Hypercubes (MOD-TRAN-based FLAASH) algorithm under the ENVI 5.3
program.
Second, the Function of mask (Fmask) algorithm was applied to detect clouds and
cloud shadows on the created cloudy maps. Finally, the mask of the study area prepared
for every single satellite image was created by overlapping the river network map and
cloudy maps. The reectance-image prepared as inputs was cleared of cloud, cloud
shadows and focused on the water area.
Depending on each object (water, soil), the spectral reectance has specied wavelengths
but the range should be in the range 01 (Peddle et al. 2001). Normally, the spectral
reectance of clear water is quite low. The wavelength reectance of seawater was small
between 400 nm and 850 nm, ranging from 0.01 to 0.14 (Xiong et al. 2012). In this study, mean
reectance of water was around 0.030.13 (Figure 2).
INTERNATIONAL JOURNAL OF REMOTE SENSING 6679
2.2.2. Salinity measurement
Saltwater data were collected at the same time with satellite imagery at 14 hydrology
stations: Vam Kenh 1 (VK1), Long Hai (LH), Hoa Binh (HB), Hoa Dinh (HD), My Thoa (MT), Binh
Dai (BD), Loc Thuan (LT), An Thuan (AT), Son Doc (SD), Giong Chom (GC), My Hoa (MH), Ben
Trai (BT), Huong My (HM) and Khanh Thanh Tan (KTT) and 3 sluice gates: Vam Kenh 2 (VK2),
Vam Giong (VG) and Xuan Hoa (XH) along the rivers: Tieu River, Dai River, Ham Luong River
and Co Chien River (Figure 1). Saltwater data were provided by Tien Giang and Ben Tre
Hydrology and Metrology Centres and Department of Agriculture and Rural Development
Tien Giang during the dry seasons (January to June) from 2013 to 2016. The hydrology
stations measured salinity using Electrical Conductivity (EC) metres manufactured by Yellow
Springs Instruments (YSI); along the transects, the measured saltwater samples were col-
lected by mixing water at 0.5 m depth and surface water for every 2 hours.
2.3. Model development
To assess eective band compositions of seven bands, multi-linear regression methods
were employed. The Multiple Linear Regression (MLR), Decision Trees (DTs) and Random
Forest (RF) model were applied to develop the relationship between salinity and
reectance from Landsat-8 OLI using R sorfware version 3.3.2. Moreover, this study
used the Step-wise model to develop reectance locations for predicting based on the
real data. The input for these models was prepared using 103 samples as the real data
set and then divided into 50:50 for training and test purpose. The best model was used
to predict salinity intrusion for the whole study area using R software and ArcGIS. The
best model was employed to detect salinity intrusion for the whole study area in the
early dry season: on 24 January 2015 and 9 February 2015.
Figure 2. Maximum, minimum and mean of reectance wavelength water area based on the actual
sample size in the whole study river reaches.
6680 P. T. B. NGUYEN ET AL.
2.3.1. Bands selection for modelling the salinity intrusion
To choose suitable bands for the model development, the reectance wavelength data from
7 bands: Band 1 Coastal/Aerosol (0.4330.453 μm), Band 2 Bule (0.4500.515 μm), Band 3
Green (0.5250.600 μm), Band 4 Red (0.6300.680 μm), Band 5 Near Infrared (0.845
0.885 μm), Band 6 Shortwave Infrared 1 (1.5601.660 μm), Band 7 Shortwave Infrared 2
(2.082.35 μm) were considered to investigate the correlation both single band and multiple
bands with salinity observation. The MLR was employed to analyse these relationships. The
probability value (p-value) and coecient of determination (R
2
) were factors to assess which
were the eective bands to use as an input to apply statistical model.
2.3.2. Modelling salinity intrusion with reectance wavelength
The MLR analysis is the most commonly applied statistical method (Owen 2001) and is
highly exible for examining the relationship between independent variables and a
single dependent variable (Aiken, West and Pitts 2003). Meanwhile, the DTs is a non-
parametric and highly nonlinear method that can deal with high-dimensional problems
where the number of features is much larger than the number of samples. The RF
regression algorithm is an ensemble learning algorithm that combines and grows trees
from a large set of the regression trees (Epifanio 2017; Breiman 2001).
The MLR, DTs and RF were considered to nd out the best model to explore the
relationship between salinity and reectance wavelength. The DTs model was integrated
in the R software by the Recursive partitioning function (Rpart). The Rparts Complexity
Parameter (CP) coecient was set as 0.01. In the RF analysis, two parameters need to be
optimized including the number of regression tree and the number of input variables
per node. This study chose the number of regression tree with a high number of 1000
trees and the number of input variables per node was set at the default value (i.e. 0.333).
2.3.3. Modelling salinity intrusion with reectance wavelength and location
The Step-wise MLR was employed for predicting salinity using variuos reectance
wavelengths of Landsat-8 OLI and the location (latitude and longitude) where salinity
was measured in situ.
Root Mean Square Error (RMSE), R
2
and p-value were used to evaluate the goodness
of t and signicance of these models.
3. Results
3.1. The relationship between reectance and salinity
The composite spectral of 7 bands including Band 1 Ultra Blue (Coastal/Aerosol),
Band 2 Blue, Band 3 Green, Band 4 Red, Band 5 Near Infrared (NIR), Band 6
Shortwave Infrared 1 (SWIR-1) and Band 7 Shortwave Infrared 2 (SWIR-2) provided
highly eective prediction signicantforthesalinitymodel(Figure 3). The composi-
tion of Band 2, Band 3, Band 4 and Band 7 was highly signicant with a p-value
(approximately, 3 × 10
9
) which was greater than the combination of 7 bands. Use of
a single band was unlikely to be productive, and only Band 3 presented a high
correlation salinity (see Figure 3). Therefore, four bands (Band 2, Band 3, Band 4 and
Band 7) were selected as inputs for developing the further salinity intrusion models.
INTERNATIONAL JOURNAL OF REMOTE SENSING 6681
3.2. Modelling salinity intrusion
The selected bands (i.e. Band 2, Band 3, Band 4 and Band 7) were used as the input of each
procedure. Figures 4-6show the observations and prediction of the MLR, DTs and RF
regression, respectively. The MLR model presented fairly good R
2
in training when the R
2
and RMSE were 50.23% and 4.15, respectively, while the test showed a very poor non-
signicant correlation with an R
2
of 22.61% and RMSE of 4.12. The range of predicted salinity
value was 020 ppt in training which was higher than in the test runs (Figure 4(a,b)). While
the DTs model indicated less signicant correlation in both training and test, the R
2
values
Figure 3. Multiple linear analysed the relationship between salinity and composite bands.
Figure 4. Scatter plot of the MLR based on (a) the real data in training with 51 training samples and (b) test
with 51 test samples.
6682 P. T. B. NGUYEN ET AL.
were 25.41% and 13.09% while the RMSE values were 2.72 and 2.83 for training and test,
respectively. Predicted salinitys range was around 515 ppt in the training as well as the test
(Figure 5(a,b)). However, RMSE of the DTs model was better than that of the MLR model for
all processing; the p-value was 9.7 × 10
5
in the DTs and 2.0 × 10
7
in the MLR.
The RF model was highly correlated to salinity in the training (i.e. R
2
and RMSE were
90.41% and 1.1, respectively). However, the test also showed the limitation of the model (R
2
and RMSE were 22.55% and 2.13, respectively). The range of predicted salinity was between
418 ppt in the training and 618 ppt in the test (Figure 6(a,b)). The RF model turn out to the
best salinity intrusion model. The p-value of the RF had a very high signicance level with
p-value<2.0×10
16
in training and p-value <0.0002 in test. Moreover, based on the result
Figure 5. Scatter plot of the DTs regression based on (a) the real data in training with 51 training
samples and (b) test with 51 test samples.
Figure 6. Scatter plot of the RF based on (a) the real data in training with 51 training samples and
(b) test with 51 test samples.
INTERNATIONAL JOURNAL OF REMOTE SENSING 6683
shown in this study, the RF performed well in the training but the testing of the model
exposed weaknesses that maybe caused by inadequate number of observations.
3.3. Reectance-location salinity modelling and mapping salinity intrusion
The reectance and location data were combined as parameters in the Step-wise model that
showed a good relationship with salinity. Figure 7(a,b) presents the regression between
predicted values and observed salinity, R
2
of training and test ordered 77.48% and 74.16%,
respectively, while RMSE was 2.57 and 2.96. However, some extraordinary predicted values
were lower than 0 ppt in both training and test where 0 ppt was exceptional in the actual
salinity observations. Thus, locality issues need to verify the model if it was used in other
study areas. The formula (1) can only be used in this particular study area, and if it is applied
to a dierent area, the weight and perhaps also the number of coecients in the model
would have to be changed. Furthermore, location played as a strong factor in the formula.
Even though the location was helpful to illustrate a general trend but it was a cause of
unrecovered essential information from reectance wavelength data.
Salinity ¼ð3:741 104Þx8:235 105

yþ1:575 102

B2
2:92 102

B3þ40:51B4þ1:048 102

B71:366 102(1)
where xis latitude; yis longitude; B
2
,B
3
,B
4
and B
7
are the Landsat-8 OLI spectral bands
(i.e. Band 2, Band 3, Band 4 and Band 7, respectively).
Mapping salinity intrusion based on the reectance-location model showed that the
salinity level clearly dierentiated between estuaries and the upstream of the river. The
Cua Tieu and Cua Dai rivers presented high salinity intrusion while the Co ChienCung
Hau River had the lowest salinity. The results demonstrated a change in saltwater
concentration and intrusion on dierent days. Mean of salinity level was 7.12 ppt and
standard deviation was 9.88 ppt on 24 January 2015 (Figure 8(a)). It was 6.44 ppt at
mean and 9.48 ppt at Standard Deviation (SD) on 9 February 2015 (Figure 8(b)).
Figure 7. Scatter plot of the stepwise regression model (reectance-location) between predicted salinity
and observed salinity (a) training with 51 training samples and (b) test with 51 test samples.
6684 P. T. B. NGUYEN ET AL.
4. Discussion
Identication bands for setting the model were very important to the accuracy of the
predictive salinity map: it means that not only does R
2
and RMSE of the modelling need
to be considered but also the composite of wavelength data set as inputs for predicting
salinity in the whole study area. On the other hand, using too many input variables can
Figure 8. Salinity intrusion from the reectance-location model; (a) 24 January 2015 mean: 7.12;
SD: 9.88 with 51 training samples; (b) 9 February 2015 mean: 6.44; SD: 9.48 with test samples.
INTERNATIONAL JOURNAL OF REMOTE SENSING 6685
lead to ttings quickly which become computationally infeasible if attempts are made to
use a higher number of potential predictor variables (Messner et al. 2016). Thus, proper
selection of the identication bands set-up for use in the model is very important for the
predictive accuracy of the salinity map.
The salinity of the sea surface can be represented by a function combining several
remotely sensed ocean colour bands (Urquhart et al. 2012). This study found that the
combination of spectral wavelength of Band 2 (Blue: 0.450.51 μm), Band 3 (Green:
0.530.59 μm),Band4(Red:0.630.67 μm)andBand7(SWIR2:2.112.29 μm) was
essential to detect salinity intrusion on the Tien River. Likewise, Wang and Xu (2008)
reported that the TM Bands 15 in Landsat-5 TM were strongly correlated with salinity.
Castillo (2005), where the study on the salinity at the Gulf of Mexico, reported that
higher salinity levels resulted in escalated reectance of coloured dissolved organic
matter (CDOM) at wavelengths less than 600 nm,which is in agreement with our results
for Band 2 and Band 3. Urquhart et al. (2012) reported the reectance wavelength of
MODIS at 488, 443 and 667 nm associated with salinity. In addition, Zhao, Temimi, and
Ghedira (2017) reported that the Landsat-8 OLIsBands14 were selected to use in the
algorithm development which is in agreement with our ndings for Landsat-8 OLIs
Bands 24. Nevertheless, there have been contradictory results reported by some
researchers. Baban (1997)andWangandXu(2008) reported that the TM Band 3 (Red:
0.630.69 μm) was the most correlative with salinity. Conversely, this study showed
thatLandsat-8OLIBand3(Green:0.530.59 μm) was the most signicant with the
salinity (see Figure 3). In a study on salinity in southwestern Australian estuaries, Lavery
et al. (1993) reported the linear negative relationship of salinity with the reectance of
TM Band 4 (NIR: 0.760.90 μm) and of TM Band 7 (SWIR: 2.082.35 μm) that agreement
with our study results with combination of Landsat-8 OLI Band 7 (SWIR 2: 2.11
2.29 μm); however, the NIR spectral bands were not selected in this study. The dis-
crepancy in relationships between salinity and water reectancewerederivedfrom
satellite data and the dierences of R
2
may have been caused by environmental of the
site-specicthatmakesdierences of some parameter in the water such as the CDOM,
TSS properties and salinity level. Moreover, the biogeochemical processes on land
divergent origins of CDOM and various concentrations of TSS in freshwater discharges
could be responsible for changes in the optical properties of CDOM (Castillo 2005)and
TSS in coastal environments (Wang and Xu 2008).
The VMD is located in the tropical monsoon region where season has a strong impact
on discharge, and tidal incursion of saltwater is characteristic during the low-ow season
(dry season), the estuarine being in partially well-mixed conditions, with saltwater
intrusion around 40 km inland, bringing ne-sediment up-river to a turbidity maximum
area. The majority of the sediment may have been deposited in shallow coastal waters
(Wolanski et al. 1996) and the current situation of estuarine sediments and open bay
muddy sediments expand more and more in the Mekong Delta region (Oanh et al.
2001). It is a challenge to detect salinity level when the number of observations might
not be enough to represent a representative sample of the study area. Meanwhile, the
study of Urquhart et al. (2012) was successful in the application of MODIS to detect
salinity intrusion in Chesapeake Bay (USA) using a huge set of data collected from 2003
to 2010 at 67 monitoring stations (620 samples). On the other hand, the data obtained
for the present study were collected from 17 stations which were measured and
6686 P. T. B. NGUYEN ET AL.
provided by dierent oces which may lead to some inherent inconsistencies and
uncertainties out of the control in the study.
Choosing a suitable model seriously eects on the accuracy of the model and is
almost as equally important as variables and is more important than sample size
(Fassnacht et al. 2014). The MLR method clearly showed the structure of model but in
cases where the relationship between variables is complex, linear regression may lack
the ability to achieve a condence level useful for predictive purposes. The DTs showed
very low potential for useful predictions of salinity. Nevertheless, the RF model is a
popular method in many elds since they can be successfully applied to complex data,
with a small sample size, complex interactions and correlations, with mixed type
predictors (Epifanio 2017). The RF model also exhibits the highest predictive capability
compared with the MLR and DTs models (Chen et al. 2017). This study showed that the
RF model was the best model to predict salinity intrusion. Unfortunately, the sample size
is not enough to present a suciently detailed prole of the study area.
The overtting problem was a big issue, which showed even in training tasks, the R
2
was rarely good enough to make useful predictions (Figure 5). The quality of satellite
images, the schedules used for measuring salinity and the timing of satellite images
were factors which limit observation in this study area. If a remote sensing program is
set up to monitor salinity intrusion, then the data set would naturally increase over time
and its predictive value would steadily improve. Another source of error is that the
remote sensing data which were used represent the integrated information on the
surface water while salinity data from the monitoring stations were taken from a specic
depth. Furthermore, special conditions like high water turbidity may aect the accuracy
of the algorithm. It is suggested that the algorithm uncertainties were attributed to the
several parameters and more measurements were required for improving the perfor-
mance of the algorithm. The application of the developed algorithm to other sites with
dierence in optical properties and environmental parameters must be cautious, and
recalibration with the local in situ measurement is necessary.
The model was acceptable when successfully applied for mapping salinity in the
whole study area. The sensitivity of the reectance-location data was examined to
recognize salinity changes. Salinity mapping distinctly divided the low salinity-low
intrusion upstream areas and high salinity-high intrusion frequency areas downstream.
The merging of reectance-location data improved upon the limitations of the single
reectance model which is in agreement with Urquhart et al. (2012) where their study of
the salinity in the Chesapeake Bay showed that the latitude and longitude are the most
signicant predictor variables in the surface salinity estimation model. This achievement
may be due to the fact that the salinity intrudes into the river as a function of the
distance from the mouth of the estuary.
Furthermore, combining remote sensing and geospatial interpolation techniques was
illustrated as signicantly improving accuracy to address the issue of limited data
availability in the coastal area (Urquhart et al. 2013). Thus, to consider location as
variables the model should be set up and updated frequently to adapt to the changing
of salinity over time. However, this method contains uncertainties due to salinity intru-
sion being inuenced by dierent factors (hydrology of rivers and weather conditions)
which cannot simply expressed by location criteria. Merging the location and reectance
INTERNATIONAL JOURNAL OF REMOTE SENSING 6687
wavelength demonstrated a good correlation with R
2
and RMSE. It is likely the best way
to develop an interpolation model.
Field observations of salinity cannot cover enough of any real-world study area.
However, the usefulness of the model may face limitations due to locality issues
(Urquhart et al. 2012). Thus, using location parameters can lead to the neglect of
important information on satellite images if the location plays too strong role in
predicting salinity.
5. Conclusion
The Landsat-8 OLI oers a convenient approach to enhance prediction capacity of saline
intrusion. This study showed that Band 2, Band 3, Band 4 and Band 7 were vital for
developing a successful reectance wavelength salinity model. The RF model was demon-
strated to maximize capacity for exploring the relationship between reectance and
salinity. However, the small sample size was a cause of overtting and limits the applica-
tion of these models for predictive purposes. Improving sample size is the most important
priority work for further study to explore more thoroughly the relationship between
salinity level and single reectance wavelength from satellite images. Ongoing use of
the model incorporating new data as it is collected will progressively improve the model.
The combination of reectance-locations for predicting salinity intrusion illustrated a
good correlation, which could be used to predict trends of salinity intrusion, when eld
observations of salinity cannot cover enough of any real-world study area. However,
locality issues should be kept in mind which can negate the reectance information in
the satellite images and limit the application of remote sensing when there is a lack of
sucient ground observational data. Even though mapping salinity of reectance-loca-
tion model clearly showed the salinity dynamic in study area, it also faced inherent
limitations due to lack of observation in upstream areas (where economic losses due to
unexpected salinity incursions would be likely to be the most severe) and locality issues
such as the suitability of monitoring station sites due to the latitude and longitude play
too strong a role for predicting salinity.
Due to the revisit frequency of 16 days for the satellite used in the present study and
the requirements of cloud-free conditions for satellite measurements especially in the
tropical area, there are very limited eld measurements acquired during OLI acquisition
times. Salinity alerts may be too late to be useful in preventing salinity damage to
Mekong agriculture.
Acknowledgements
This work was supported by the Higher Education Research Promotion and the Thailands
Education Hub for Southern Region of ASEAN Countries Project Oce of the Higher Education
Commission, under Prince of Songkla University. The authors are thankful to Dr. Raymond J Ritchie
who gave a lot of useful advice for this manuscript.
Disclosure statement
No potential conict of interest was reported by the authors.
6688 P. T. B. NGUYEN ET AL.
Funding
This work was supported by the Higher Education Research Promotion and the Thailands
Education Hub for Southern Region of ASEAN Countries Project Oce of the Higher Education
Commission, under Prince of Songkla University.
ORCID
Werapong Koedsin http://orcid.org/0000-0002-4411-9148
References
Aiken, L. S., S. G. West, and S. C. Pitts. 2003.Multiple Linear Regression.In Handbook of
Psychology, edited by I. B. Weiner. New York, NY: John Wiley & Sons. doi:10.1002/0471264385.
wei0219
Baban, S. M. J. 1997.Environmental Monitoring of Estuaries; Estimating and Mapping Various
Environmental Indicators in Breydon Water Estuary, U.K., Using Landsat TM Imagery.Estuarine,
Coastal and Shelf Science 44: 589598. doi:10.1006/ecss.1996.0142.
Binh, N. T. 2015.Vulnerability and Adaptation to Climate Change.[PhD thesis.], The Faculty of
Agriculture, Bonn University and Institute for Environment and Human Security, United Nations
University (UNU-EHS), Germany. http://hss.ulb.uni-bonn.de/2015/3924/3924.pdf.
Breiman, L. 2001.Random Forests.Machine Learning 45: 532. doi:10.1023/A:1010933404324.
Castillo, C. E. D. 2005.Remote Sensing of Organic Matter in Coastal Waters. Chap.7.In Remote
Sensing of Coastal Aquatic Environments, edited by R. L. Miller, C. E. D. Castillo, and B. A. McKee,
157180. The Netherlands: Springer.
CGIAR Research Centers in Southeast Asia. 2016.The Drought and Salinity Intrusion in the
Mekong River Delta of Vietnam.Accessed June 25 2016. https://cgspace.cgiar.org/rest/bit
streams/78534/retrieve/.
Chen, W., X. Xie, J. Wang, B. Pradhan, H. Hong, D. T. Bui, Z. Duan, and J. Ma. 2017.A Comparative
Study of Logistic Model Tree, Random Forest, and Classication and Regression Tree Models for
Spatial Prediction of Landslide Susceptibility.Catena 151: 147160. doi:10.1016/j.
catena.2016.11.032.
DSa, E. J., J. B. Zaitze, C. S. Yentsch, J. L. Miller, and R. Ives. 2002.Rapid Remote Assessments of
Salinity and Ocean Color in Florida Bay.In The Everglades, Florida Bay, and Coral Reefs of the
Florida Keys: An Ecosystem Sourcebook, edited by J. Porter. Boca Raton, FL: CRC Press.
Deltares, Delta Alliance and Federation of Water Resources Planning and Investigation in the
South Vietnam.2011.Vietnam-Netherlands Mekong Delta Masterplan Project Mekong Delta
Water Resources Assesment Studies, Viet nam-Neetherlands Mekong Delta Master
Plan.Accessed 15 January 2017. https://www.wur.nl/upload_mm/2/c/3/b5f2e669-cb48-4ed7-
afb6-682f5216fe7d_mekong.pdf
Dev, S., B. Wen, Y. H. Lee, and S. Winkler. 2016.Machine Learning Techniques and Applications for
Ground-Based Image Analysis.IEEE Geoscience and Remote Sensing 4: 7993. doi:10.1109/
MGRS.2015.2510448.
Epifanio, I. 2017.Intervention in Prediction Measure: A New Approach to Assessing Variable Importance
for Random Forests.Epifanio BMC Bioinforma 18: 116. doi:10.1186/s12859-017-1650-8.
Fang, L., S. Chen, H. Wang, J. Qian, and L. Zhang. 2010.Detecting Marine Intrusion into Rivers
Using EO-1 ALI Satellite Imagery: Modaomen Waterway, Pearl River Estuary, China.International
Journal of Remote Sensing 31 (15): 41254146. doi:10.1080/01431160903229218.
Fassnacht, F. E., F. Hartig, H. Lati, C. Berger, J. Hernández, P. Corvalán, and B. Koch. 2014.
Importance of Sample Size, Data Type and Prediction Method for Remote Sensing-Based
Estimations of Aboveground Forest Biomass.Remote Sensing of Environment 154: 102114.
doi:10.1016/j.rse.2014.07.028.
INTERNATIONAL JOURNAL OF REMOTE SENSING 6689
Hashimoto, T. R. 2001.Environmental Issues and Recent Infrastructure Development in the Mekong
Delta: Review, Analysis and Recommendations with Particular Reference to Largescale Water
Control Projects and the Development of Coastal Areas (No. 4). Sydney, Australia: Australian
Mekong Resource Centre, University of Sydney. Accessed 15 January 2017. http://sydney.edu.
au/mekong/documents/wp4.pdf.
Himi, M., S. Benabdelouahab, A. Salhi, L. Rivero, M. Elgetta, A. El, J. Stitou, and A. Casas. 2017.
Geophysical Characterization of Saltwater Intrusion in a Coastal Aquifer : The Case of Martil-
Alila Plain (North Morocco).Journal of African Earth Sciences African Earth Sciences 126: 136
147. doi:10.1016/j.jafrearsci.2016.11.011.
Khang, N. D., A. Kotera, T. Sakamoto, and M. Yokozawa. 2008.Sensitivity of Salinity Intrusion to
Sea Level Rise and River Flow Change in Vietnamese Mekong Delta-Impacts on Availabilityof
Irrigation Water for Rice Cropping.Journal of Agricultural Meteorology 64: 167176. doi:10.2480/
agrmet.64.3.4.
Lavery, P., C. Pattiaratchi, A. Wyllie, and P. Hick. 1993.Water Quality Monitoring in Estuarine
Waters Using the Landsat Thematic Mapper.Remote Sensing of Environment 46: 268280.
doi:10.1016/0034-4257(93)90047-2.
Liu, R., and D. F. Gillies. 2016.Overtting in Linear Feature Extraction for Classication of High-
Dimensional Image Data.Pattern Recognition 53: 7386. doi:10.1016/j.patcog.2015.11.015.
Messner, J. W., G. J. Mayr, A. Zeileis, J. W. Messner, G. J. Mayr, and A. Zeileis. 2016.
Nonhomogeneous Boosting for Predictor Selection in Ensemble Postprocessing.American
Meteorological Society 145: 137147. doi:10.1175/MWR-D-16-0088.1.
Nguyen, A. D., and H. H. G. Savenije. 2006.Salt Intrusion in Multi-Channel Estuaries: A Case Study
in the Mekong Delta, Vietnam.Hydrology and Earth System Sciences Sci 3 (2): 499527.
doi:10.5194/hessd-3-499-2006.
Nguyen, A. D., H. H. G. Savenije, D. N. Pham, and D. T. Tang. 2008.Using Salt Intrusion
Measurements to Determine the Freshwater Discharge Distribution over the Branches of a
Multi-Channel Estuary: The Mekong Delta Case.Estuarine, Coastal and Shelf Science 77: 433
445. doi:10.1016/j.ecss.2007.10.010.
Noh, S., M. Choi, E. Kim, N. P. Dan, B. X. Thanh, N. T. V. Ha, S. Sthiannopkao, and S. Han. 2013.
Inuence of Salinity Intrusion on the Speciation and Partitioning of Mercury in the Mekong
River Delta.Geochimica Et Cosmochimica Acta 106: 379390. doi:10.1016/j.gca.2012.12.018.
Oanh, T. K. T., N. V. Lap, M. Tateishi, I. Kobayashi, and Y. Saito. 2001.Sedimentary Facies, Diatom
and Foraminifer Assemblages in a Late PleistoceneHolocene Incised-Valley Sequence from the
Mekong River Delta, Bentre Province, Southern Vietnam. The BT2 Core.Journal of Asian Earth
Sciences 20: 8394. doi:10.1016/S1367-9120(01)00028-1.
Owen, A. B. 2001.““Regression and Modelling.Chap. 4.In Empirical Likelihood.BocaRaton,FL:
Chapman and Hall.
Peddle, D. R., H. P. White, R. J. Soer, J. R. Miller, and E. F. Ledrew. 2001.Reectance Processing of
Remote Sensing Spectroradiometer Data.Computers & Geosciences 27 (2011): 203213.
doi:10.1016/S0098-3004(00)00096-0.
Ratner, B. 2011.Overtting: Old Problem, New Solution. Chap.27.In Statistical and Machine-
Learning Data Mining Techniques for Better Predictive Modeling and Analysis of Big Data. 2nd ed.
Taylor & Francis Group. Boca Raton, FL: CRC Press.
Roy, P. K., S. S. Roy, A. Giri, G. Banerjee, A. Majumder, and A. Mazumdar. 2014.Study of Impact on
Surface Water and Groundwater around Flow Fields Due to Changes in River Stage Using
Groundwater Modeling System.Clean Technologies and Environmental Policy 17: 145154.
doi:10.1007/s10098-014-0769-9.
Shcheglovitova, M., and R. P. Anderson. 2013.Estimating Optimal Complexity for Ecological Niche
Models: A Jackknife Approach for Species with Small Sample Sizes.Ecological Modelling 269: 9
17. doi:10.1016/j.ecolmodel.2013.08.011.
Trung, N. H., C. H. Hoanh, T. P. Tuong, X. H. Hien, L. Q. Tri, V. Q. Minh, D. K. Nhan, P. T. Vu, and V. P.
D. Tri. 2016.Climate Change Aecting Land Use in the Mekong Delta: Adaptation of Rice-Based
Cropping Systems (CLUES) Theme 5: Integrated Adaptation Assessment of Bac Lieu Province
and Development of Adaptation Master Plan.Accessed 3 January 2017 https://www.research
6690 P. T. B. NGUYEN ET AL.
gate.net/publication/301612048_Climate_change_aecting_land_use_in_the_Mekong_Delta_
Adaptation_of_rice-based_cropping_systems_CLUES_ISBN_978-1-925436-36-5.
Trung, N. H., and V. P. D. Tri. 2014.Possible Impacts of Seawater Intrusion and Strategies for Water
Management in Coastal Areas in the Vietnamese Mekong Delta in the Context of Climate
Change.In Coastal Disasters and Climate Change in Vietnam, Waltham, edited by Nguyen
Danh Thao Hiroshi Takagi Miguel Esteban. USA: Elsevier. doi:10.1016/B978-0-12-800007-
6.00010-1.
Urquhart, E. A., B. F. Zaitchik, M. J. Homan, R. R. Murphy, and B. F. Zaitchik. 2013.Geospatial
Interpolation of MODIS-derived Salinity and Temperature in the Chesapeake Bay.Remote
Sensing of Environment 135: 167177. doi:10.1016/j.rse.2013.03.034.
Urquhart, E. A., B. F. Zaitchik, M. J. Homan, S. D. Guikema, and E. F. Geiger. 2012.Remote Sensing
of Environment Remotely Sensed Estimates of Surface Salinity in the Chesapeake Bay : A
Statistical Approach.Remote Sensing of Environment 123: 522531. doi:10.1016/j.
rse.2012.04.008.
Wang, F., and Y. Xu. 2012.Remote Sensing to Predict Estuarine Water Salinity.In Environmental
Remote Sensing and Systems Analysis, edited by N. B. Chang, 85-107. Boca Raton, FL: Taylor &
Francis Group/CRC Press.
Wang, F., and Y. J. Xu. 2008.Development and Application of a Remote Sensing-Based Salinity
Prediction Model for a Large Estuarine Lake in the US Gulf of Mexico Coast.Journal of
Hydrology 360: 184194. doi:10.1016/j.jhydrol.2008.07.036.
Waske, B., M. Fauvel, J. A. Benediktsson, and J. Chanussot. 2009.Machine Learning Techniques in
Remote Sensing Data Analysis.In Kernel Methods for Remote Sensing Data Analysis, edited by G.
C. Valls and L. Bruzzone. Chichester, UK: John Wiley & Sons.
Wolanski, E., N. N. Huan, L. T. Dao, N. H. Nhan, and N. N. Thuy. 1996.Fine-Sediment Dynamics in
the Mekong River Estuary, Vietnam.Estuarine, Coastal and Shelf Science 43: 565582.
doi:10.1006/ecss.1996.0088.
Xiong, Y. J., G. Y. Qiu, X. H. Chen, S. L. Tan, and H. X. Feng. 2012.Hyperspectral Characteristics of
Seawater Intrision in Pearl River Delta, China Based on Laboratory Experiments.In Geoscience
and Remote Sensing Symposium (IGARSS), Proceeding of the IEEE InternationalConference on
Munich, Germany, July 22-27.
Zhao, J., M. Temimi, and H. Ghedira. 2017.Remotely Sensed Sea Surface Salinity in the Hyper-
Saline Arabian Gulf: Application to Landsat 8 OLI Data.Estuarine, Coastal and Shelf Science 187:
168177. doi:10.1016/j.ecss.2017.01.008.
Zhou, F., and A. Zhang. 2016.Optimal Subset Selection of Time-Series MODIS Images and Sample
Data Transfer with Random Forests for Supervised Classication Modelling.Sensors(Switzerland)
16: 118. doi:10.3390/s16111783.
INTERNATIONAL JOURNAL OF REMOTE SENSING 6691
... Salinity is a key physical parameter as it affects the water quality, growth, and development of the aquatic vegetation and different animal species (Meier et al., 2011). Water salinity can cause significant damages but are arduous to detect, on the short and long timescale, and it acts as a slow-onset hazard (Nguyen et al., 2018). Water salinity is a complex process depending on many factors; These include freshwater discharge from upstream, capacity and morphology of the channel, configuration of the drainage network, tidal conditions, and the presence of control structures (Nguyen et al., 2018). ...
... Water salinity can cause significant damages but are arduous to detect, on the short and long timescale, and it acts as a slow-onset hazard (Nguyen et al., 2018). Water salinity is a complex process depending on many factors; These include freshwater discharge from upstream, capacity and morphology of the channel, configuration of the drainage network, tidal conditions, and the presence of control structures (Nguyen et al., 2018). ...
... Recognition bands were essential for setting the model to match the accuracy of the predictive water salinity map (Nguyen et al., 2018). Moreover, too many variables can result in fitting fast, which would be, in fact, impractical if a higher number of potential predictor variables are used (Messner et al., 2017). ...
Article
Full-text available
Water salinity is a key physical parameter that affects water quality, growth, and development of the aquatic vegetation and animals. The salinity of Karun River has been increasing due to some critical factors, e.g., severe climate condition and regional physiography, industrial sources, domestic and urban sewerage, irrigation of agricultural land, fish hatchery, hospital sewage, and high tide level of Persian Gulf. This study aimed at building regression models to ascertain the water salinity through the relationship between the reflectance of the Landsat-8 OLI and In situ measurements. Accordingly, 102 In situ measurements have been collected from June 2013 to July 2018 along the Karun River, subsequently measured data was divided into 70:30 for training and test purposes. Besides, the Sobol' sensitivity analysis was applied to determine the best bands combination from the performance standpoint. The results of the Sobol' sensitivity analysis revealed that band 1-Coastal/Aerosol (0.433-0.453 µm), band 2-Blue (0.450-0.515 µm) and band 3-Green (0.525-0.600 µm) are the best combinations and showed that Landsat-8 OLI band 2 has the closest correlation with the salinity. Furthermore, to have a comprehensive investigation, the Ordinary Least Square (OLS), Support Vector Regression (SVR), and Multi-Layer Perceptron 2 (MLP) methods were applied. The number of layers and nodes in the MLP neural network is optimized using the Genetic Algorithm (GA), and GA has selected four layers and three neurons per layer. The OLS, SVR and MLP+GA models resulted in values of and RMSE for test data, í µí± 2 which are respectively obtained to be 0.68 and 411 , 0.72 and 376 and 0.78 and μs cm-1 μs cm-1 363. Therefore, MLP+GA has had the best performance and accuracy. However, the μs cm-1 corresponding values are acceptable considering the fact that the range of field data extensively changes from 385 and 4310. Eventually, water salinity maps were prepared by OLS, SVR and MLP+GA methods to demonstrate the water salinity on 1 February 2015 and 5 September 2018, afterward change detection maps were prepared to assess the water salinity on 1 February 2015 and 5 September 2018. The change detection maps illustrate that the pertinent salinity on 5 September 2018 is lower as compared to the data obtained on 1 February 2015, because not only the rainfall has increased, but the cane sugar cultivation has also decreased which is one of the effective factors on the salinity of the water.
... To estimate SSC, Islam et al. (2002) used the single green band of Landsat-5 TM in the same coastal sea in the Bay of Bengal, Wong et al. (2007) used the single green band of MODIS in Hong Kong. Similarly, at the Vietnamese Mekong Delta, the use of a green band of Landsat-8 OLI presented the highest correlation with salinity in the single-band selection (Nguyen et al. 2018). However, Nguyen et al. (2018) recommended multi-band combinations to enhance the sensitivity of surface water. ...
... Similarly, at the Vietnamese Mekong Delta, the use of a green band of Landsat-8 OLI presented the highest correlation with salinity in the single-band selection (Nguyen et al. 2018). However, Nguyen et al. (2018) recommended multi-band combinations to enhance the sensitivity of surface water. The blue-to-green band ratio is a more popular index to estimate salinity and other water-related variables (Ahn et al. 2008;Son et al. 2012). ...
Article
Full-text available
Summer rice cannot be grown near the coast of the Ayeyarwady Delta, Myanmar, because of the high salinity in river water during the dry season. This means that saline intrusion should be monitored to manage the irrigated rice-growing area. The aim of this study therefore is to develop a model to estimate the salinity of river water using satellite imagery. The imagery of Sentinel-2 was suitable for monitoring saline intrusion because of their high spatial (10-m) and temporal (10-day) resolutions. We found that the reflectance of the visible bands was correlated with electrical conductivity, which was influenced by the concentration and composition of dissolved salts. When the river water mixed with the salt water from the sea, suspended particles tended to flocculate and settle, as a result, less turbid water was more saline. The best-fitting model was obtained with the green band (coefficient of determination R ² of 0.776, root mean square error of 4.896 dSm ⁻¹ , and mean absolute error of 3.340 dS m ⁻¹ ). The saline intrusion showed considerable spatial and temporal variability during the dry season. The salinity intrusion extended approximately 80 km inland at the end of the dry season in March in the Pathein River. The 1 ppt salt concentration line in March marked the boundary between cultivated and non-cultivated areas of paddy field, which indicates that cultivable areas were strongly affected by saline intrusion. The results show that more frequent and higher resolution monitoring than before of the Sentinel-2 can support effective water resource management.
... The optimum electromagnetic wavelength for measuring salinity is determined by using the microwave emission from the ocean surface [28]. There is a good correlation between the salinity and reflectance data when adding the locations of salinity measured stations as a parameter of the Step-wise model [22] Medium-resolution satellite image data has been successfully used to determine the water quality parameters, although it's designed for terrestrial applications [3,4]. ...
Article
Burullus lake is one of the coastal lakes in northern Egypt. Burullus lake is connected to seven drains through its western, eastern, and southern shores. The discharge of untreated wastewater (domestic, industrial, and agricultural) from these drains caused degradation for the water quality of the lake. Therefore, it is needed to develop a methodology to monitor water quality parameters at a low cost. This study is a trial to estimate water quality parameters from remote sensing data (reflectance data) by developing statistical regression models. Sentinel-2 reflectance data are compared to field measurements. The field measurements include transparency (SDT), chlorophyll-a concentration (Chl-a), total nitrogen (TN), total phosphorus (TP), and salinity. The coefficient of determination (R2) and normalized root mean square error (NRMSE) are calculated to evaluate the goodness of fit between field measurements and reflectance values. The results show that the optimum bands and bands ratios to estimate SDT, Chl-a, TN, TP, and Salinity are B6/B7, B7/B8, B8A, B8/B3, and B3/B8, respectively. The developed regression model is acceptable to be used for detecting water parameters and the produced R2 and NRMSE are within the range from 0.52 to 0.83 and from 0.12 to 0.34, respectively. The distribution maps of water quality parameters were built using the regression equations by writing these equations in the raster calculator as raster calculation expression. The results of this study show that both optical and non-optical water quality parameters are reasonably correlated with Sentinel-2 reflectance data as a low-cost data source.
... The advantages of machine learning in nonlinear regression fitting have promoted its widespread use in quantitative remote sensing. Many machine learning algorithms, such as partial least squares regression (PLSR, Song et al., 2014), support vector regression (SVR, X. , random forest regression (RFR, Alevizos, 2020;Du et al., 2018;Nguyen et al., 2018;Sagawa et al., 2019), XGBoost Cui et al., 2021;Nguyen et al., 2021;Tiyasha et al., 2021), ANN (Chen et al., 2004;Chen et al., 2021;Feng et al., 2020;Liu et al., 2015;Medina-Lopez & Urena-Fuentes, 2019), and long short-term memory (Mohebzadeh & Lee, 2021;Sagan et al., 2020;Yu et al., 2020), have been widely used to estimate water environment characteristics, including Chla, SPM, sea surface salinity, and temperature. While ensuring that the spectral characteristics are highly correlated with water quality parameters, PLSR maximizes the variance of the main components of sensitive bands and water quality parameters. ...
Article
Full-text available
Accurate water extraction and quantitative estimation of water quality are two key and challenging issues for remote sensing of water environment. Recent advances in remote sensing big data, cloud computing, and machine learning have promoted these two fields into a new era. This study reviews the operating framework and methods of remote sensing big data for water environment monitoring, with emphasis on water extraction and quantitative estimation of water quality. The following aspects were investigated in this study: (a) image data source and model evaluation metrics; (b) state‐of‐the‐art methods for water extraction, including threshold‐based methods, water indices, and machine learning‐based methods; (c) state‐of‐the‐art models for quantitative estimation of water quality, including empirical models, semi‐empirical/semi‐analytical models, and machine learning‐based models; (d) some shortcomings and three challenges of current remote sensing big data for water environment monitoring, namely the new data gap caused by massive heterogeneous data, inefficient water environment monitoring due to “low spatiotemporal resolution,” and low accuracy of water quality estimation models resulting from complex water composition and insufficient atmospheric correction methods for water bodies; and (e) five recommendations to solve these challenges, namely, using cloud computing and emerging sensors/platforms to monitor water changes in intensive time series, establishing models based on ensemble machine learning algorithms, exploring quantitative estimation models of water quality that couple physics and causality, identifying the missing elements in water environment assessments, and developing new governance models to meet the widespread applications of remote sensing of water environment. This review can help provide a potential roadmap and information support for researchers, practitioners, and management departments in the theoretical exploration and innovative application of remote sensing big data for water environment monitoring.
... Radar and optical technologies supply universal and long-lasting information around the globe, which has been proved from the detection and visualization of the Earth's surface (Farahmand and Sadeghi, 2020;Wu et al., 2020). In the recent years, several studies have successfully monitored soil salinity using the available optical remote sensing data, such as Landsat 8 OLI and Sentinel 2 (Moussa et al., 2020;Nguyen et al., 2018). These approaches focus on a combination of bands. ...
Article
With population growth, the demand for land resources is expected to increase significantly in the coming decades. Maintaining the integrity of soil distribution requires a remarkable amount of work to deal with agricultural extension. Salinity intrusion monitoring is a crucial process, which directly affects sustainable development, especially in areas affected by global warming and in coastal zones. In recent years, various studies have used the soil-water salinity data to evaluate the spatiotemporal increase in salinity intrusion. This study aims to establish a novel framework for monitoring salinity intrusion using remote sensing and machine learning. It focuses on the salinity intrusion in soil, which affects water availability, food security, human health, etc. Numerous algorithms have been implemented to find the best solution for this issue, including Xgboost (XGR), Gaussian processes, support vector regression, deep neural networks, and the grasshopper optimization algorithm (GOA). A total of 143 samples collected from 2016 to 2020 at 39 measurement stations were divided into two sets: 70% training and 30% testing. Thirty-one independent variables were used to develop the model. Vietnam's Mekong Delta, where the salinity intrusion problem is becoming increasingly serious due to global warming and demographics, was selected as the study area. Each of the proposed models was compared and evaluated by applying various statistical indices such as the root mean square error, coefficient of determination (R²), and mean absolute error. The results show that the prediction model was built successfully by wielding data from the implemented salinity measurement stations, and the XGR-GOA model was better than the other models (R² = 0.86, RMSE = 0.076, and MAE = 0.065). This finding demonstrates the feasibility of estimating and monitoring salinity intrusion in data-limited regions by integrating optical satellite images and machine learning, which are easily and cost-effectively obtainable. The proposed conceptual methodology in our study is novel and provides additional useful information for the monitoring and management of salinity intrusion not only in Vietnam's Mekong Delta, but also in other sites that have similar natural and anthropological conditions.
... In another study, Astaras and Oikonomidis (2006) have used high-resolution Landsat and Thematic mapper (TM) satellite images to delineate the seawater affected coastal areas in central Greece. Nguyen et al. (2018) have also predicted seawater intrusion in the Mekong Delta, Vietnam based on Landsat reflectance. Later, the Landsat images have also been used to assess the soil salinity of the region (Nguyen et al., 2020). ...
Article
Full-text available
Massive withdrawal of groundwater resources due to population growth and rapid industrialization has led to seawater intrusion into the coastal aquifers across the globe. The problem is an emerging challenge as the coastal areas host≈40% of the total global population. Impacts of the seawater intrusion on the health of the local community, economic and socio-cultural developments in the coastal areas have led to a wide variety of research being conducted. The objective of the present study is to provide a detailed review of the processes that control the seawater intrusion into the coastal aquifers and the necessary measures to mitigate the same. Various methods of investigation and their applicability are explained. Finally, the status of seawater intrusion in India has been discussed in greater detail.
... SI is a complex phenomenon depending on a variety of variables include freshwater discharge from upstream, capacity, and morphology of the rivers/canals, a configuration of the drainage network, tidal conditions, and presence of control artificial structures such as dams, sluice gates 3,4 . Moreover, the impacts of climate change and sea-level rise also exacerbate the damage of SI 5 . However, SI might be predicted by using statistical models. ...
Article
Full-text available
Introduction: Ham Luong River is a branch of Mekong River located in Ben Tre Province, which has played a crucial role in supporting livelihoods of local residents and the province's economic development. However, the saline intrusion has been expanding in Ham Luong River, which seriously affects the productive agriculture, aquaculture, and further causes tremendous difficulties for local people's lives. Thus, it is crucial to have research for forecast the saline intrusion in Ham Luong River. Our aim was to develop mathematical models in order to forecast the saline intrusion in Ham Luong River, Ben Tre Province. Methods: The Auto regressive integrated moving average (ARIMA) model was built to forecast the weekly saline intrusion in Ham Luong River, which has been obtained from Ben Tre Province's Hydro-Meteorological Forecasting Center over eight years (from 2012 to 2019). Results: The saline concentration increased from January to March and then decreased from April to June. The highest salinity occurred in February and March while the lowest salinity was observed in early June. Moreover, the ARIMA technique provided an adequate predictive model for a forecast of the saline intrusion in An Thuan, Son Doc, and An Hiep station. However, the ARIMA model in My Hoa and Vam Mon might be improved upon by other forecasting methods. Conclusion: Our study suggested that the nonseasonal/seasonal ARIMA is an easy-to-use modeling tool for a quick forecast of the saline intrusion.
Article
Full-text available
Determining coastal boundaries on land is essential to understanding the process of soil salinization. Once, It can be observed, and the coastal boundaries may help explain these areas' damage levels. This study aimed to observe the change in soil salinity and saltwater intrusion and use both values to determine the coastal boundaries in Subang, Indramayu, and Cirebon regencies. This study employed a multi-temporal data of Landsat 5 TM and Landsat 8 OLI-TIRS satellite imageries (2009–2015), the water spectral reflectance collected from the field survey, and the elevation data to gain the elevation information. The corrected Landsat and water reflectance data were combined and processed to obtain the saltwater intrusion using soil salinity index (SSI), salinity index (SI), brightness index (BI), normalized difference salinity index (NDSI), soil salinity index (SSI), and water salinity index (WSI). Besides that, five linear and multiple regression equations as a semi-empirical model, namely saltwater intrusion index (SWII), are also used. Only BI, SSI, and two SWII models show reasonable saltwater intrusion with 44%, 24%, and 52% accuracy. These models with below 0.2 (dS/m) represented the non-saline, while others used the saline regime to determine the boundaries. The spatial distribution of saltwater intrusion may become unreliable since its accuracy does not always relate to the land cover. Since the acceptable models mostly elucidate that the entire region in Indramayu regency has been experiencing saltwater intrusion since 2015, the boundaries are far from the coastline.
Article
Coastal aquifers are vulnerable to salinisation due to seawater intrusion. Lineaments generally play the role of pathways for this intrusion. This paper investigates the lineament pattern in the region of southern-Cameroon with the main purpose of understanding the mechanism of the eventual contamination of groundwater by salinity. 472 lineaments are mapped in the study area using both Landsat-8 OLI and 7 ETM + images. 15 of those lineaments connect 19 contaminated boreholes to the shore. A total of 24 out of 58 boreholes are contaminated by seawater. A statistical analysis of this network depicts the responsibility of lineaments in seawater intrusion. Other aggravating factors are elevation (<100 m) and slope (<7°). A wide NE-SW-oriented fractured zone is detected within the flat area extending between Mount-Cameroon and Limbe-Mabeta Massif. Furthermore, several new fractured zones are highlighted, and will be considered when elaborating policy of local water management. This low-cost and time-saving approach which combines remote sensing and GIS has been effective, and recommended for similar investigations worldwide. A geophysical campaign with the purpose of characterizing local aquifer and upgrade hydrological, geological and electrical parameters of the local aquifer is scheduled.
Article
Full-text available
Introduction: The Karun River is the biggest river basin in Iran, which supplies water demands of about 16 cities, several villages, thousands of hectares of agricultural. This river polluted because of domestic and urban sewerage, industrial sources, and irrigation of agricultural land, Hospital sewage and high tide level of Persian Gulf. Therefore, because of the importance of this river, the water salinity of this river is determined in this study. The traditional methods of determining water salinity are costly in comparison with remote sensing methods. In the present study, Landsat 8 (OLI) data was used to calculate the water salinity map for Karun River since not only it is free, but it also has an acceptable resolution. Materials and Methods: Landsat 8 (OLI) images were used to calculate reflectance for a pixel and were attained from (US Geological Survey (USGS) 2019). First, radiometric correction was applied to normalize satellite images. This process convert Digital Number into radiance. Second, in order to attain the surface reflectance values, the process of atmospheric correction was applied using the Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH). Water salinity was calculate by Iran Water and Power Recourses Development Company. Eight stations are located in the crucial point for EC measuring ALIKALE, GOTVAND, SHOOSHTAR, SHOTEYT, GARGAR, DEZ, AHVAZ, and ABADAN. Iran Water and Power Recourses Development Company obtained 102 observed EC samples from June 2013 to July 2018 along the Karun River. The Support Vector Machine was classically used for classification, Support Vector Classification, but extended for using along with regression issue, namely Support Vector Regression. The results related to the quality of the SVR depend on some factors: the loss function Ɛ, the error penalty factor C and the kernel function parameters. Usually, radial basis kernel function (RBF), k(x, x΄) = k(x,x΄)=exp⁡〖( -||x-x΄〗 2/σ^2), has been used in remote sensing studies, so, it is implemented in this study. Finally, the Genetic Algorithm (GA) is employed to optimize some parameters including C, Ɛ and σ. GA is an optimization technique create by Holland (1975) and discussed the mechanism of GA in solving nonlinear optimization problems. Besides, the Genetic Algorithm (GA) was applied to determine the best performer bands combination. Furthermore, we employ GA to optimize SVR parameters and number of layers and neurons of MLP neural network in order to maximize model accuracy. Results and Discussion: Salinity intrusion is a complex issue in coastal, hot, and dry areas. Currently, remote sensing techniques have been widely used to monitor water salinity changes, ranging from inland river networks to deep oceans. The Karun River basin, with a basin area of 67,000 km^2, is located in the southern part of Iran. The salinity of Karun River has been increasing due to some critical factors, e.g. severe climate condition and regional physiography, industrial sources, domestic and urban sewerage, irrigation of agricultural land, fish hatchery, hospital sewage, and high tide level of Persian Gulf . This study aimed at building Support Vector Regression (SVR) and Multilayer Perceptron (MLP) models to realize the salinity intrusion through the relationship between reflectance from the Landsat-8 Operational Land Imager images and salinity levels measured in situ. 102 observed samples were divided into 75% training and 25% test. Besides, the Genetic Algorithm (GA) was applied to determine the best performer bands combination. Furthermore, we employ GA to optimize SVR parameters and number of layers and neurons of MLP neural network in order to maximize model accuracy. The result showed that the MLP approach was the better model to estimate water salinity along the Karun River network in the study area, which coefficient of determination (R^2) and RMSE of test data is obtained as 0.73 and 390μs 〖cm〗^(-1). GA analysis proved that bands 1, 2 and 3 are the best for modeling water salinity. In this study, the GA is used to determine the SVR meta-parameters including the loss function Ɛ, the error penalty factor C and σ parameters, which are obtained to be〖1×10〗^(-9), 1099 and 0.96, respectively, and number of layers and neurons of MLP neural network, which are obtained to be 5 and 35, respectively. The result showed that the MLP approach was the better model to estimate water salinity along the Karun River network in the study area, which coefficient of determination (R^2) and RMSE of test data is obtained as 0.73 and 390μs 〖cm〗^(-1). Conclusion: The present study calculated the relationship between reflectance retrieved from Landsat-8 OLI and water salinity in the Karun River. SVR and MLP models had acceptable operation by considering the large size, geographic complexity of the study domain and the wide range of field data that change between 385 and 4310μs cm^(-1). Augmentation field data is the critical priority work for future study to probe the relationship between water salinity and satellite images.In addition, the contribution of thermal bands can help to increase accuracy of models. Salinity intrusion is a complex issue in coastal and hot and dry areas. Currently, remote sensing techniques have been widely used to monitor water salinity changes, ranging from inland river networks to deep oceans. The Karun River basin, with a basin area of 67,000 km2, is located in the southern part of Iran. The salinity of Karun River has been increasing due to some critical factors, e.g. severe climate condition and regional physiography, industrial sources, domestic and urban sewerage, irrigation of agricultural land, fish hatchery, hospital sewage, and high tide level of Persian Gulf .This study aimed at building Support Vector Regression (SVR) and Multilayer Perceptron (MLP) models to realize the salinity intrusion through the relationship between reflectance from the Landsat-8 Operational Land Imager images and salinity levels measured in situ. A total of 102 observed samples were divided into 75% training and 25% test. Besides, the Genetic Algorithm (GA) was applied to determine the best performer bands combination. Furthermore, we employ GA to optimize SVR parameters and number of layers and neurons of MLP neural network in order to maximize model accuracy. The result showed that the MLP approach was the better model to estimate water salinity along the Karun River network in the study area, which coefficient of determination (R2) and RMSE of test data is obtained as 0.73 and 390μscm-1
Article
Full-text available
Background Random forests are a popular method in many fields since they can be successfully applied to complex data, with a small sample size, complex interactions and correlations, mixed type predictors, etc. Furthermore, they provide variable importance measures that aid qualitative interpretation and also the selection of relevant predictors. However, most of these measures rely on the choice of a performance measure. But measures of prediction performance are not unique or there is not even a clear definition, as in the case of multivariate response random forests. MethodsA new alternative importance measure, called Intervention in Prediction Measure, is investigated. It depends on the structure of the trees, without depending on performance measures. It is compared with other well-known variable importance measures in different contexts, such as a classification problem with variables of different types, another classification problem with correlated predictor variables, and problems with multivariate responses and predictors of different types. ResultsSeveral simulation studies are carried out, showing the new measure to be very competitive. In addition, it is applied in two well-known bioinformatics applications previously used in other papers. Improvements in performance are also provided for these applications by the use of this new measure. Conclusions This new measure is expressed as a percentage, which makes it attractive in terms of interpretability. It can be used with new observations. It can be defined globally, for each class (in a classification problem) and case-wise. It can easily be computed for any kind of response, including multivariate responses. Furthermore, it can be used with any algorithm employed to grow each individual tree. It can be used in place of (or in addition to) other variable importance measures.
Article
Full-text available
Nowadays, various time-series Earth Observation data with multiple bands are freely available, such as Moderate Resolution Imaging Spectroradiometer (MODIS) datasets including 8-day composites from NASA, and 10-day composites from the Canada Centre for Remote Sensing (CCRS). It is challenging to efficiently use these time-series MODIS datasets for long-term environmental monitoring due to their vast volume and information redundancy. This challenge will be greater when Sentinel 2-3 data become available. Another challenge that researchers face is the lack of in-situ data for supervised modelling, especially for time-series data analysis. In this study, we attempt to tackle the two important issues with a case study of land cover mapping using CCRS 10-day MODIS composites with the help of Random Forests’ features: variable importance, outlier identification. The variable importance feature is used to analyze and select optimal subsets of time-series MODIS imagery for efficient land cover mapping, and the outlier identification feature is utilized for transferring sample data available from one year to an adjacent year for supervised classification modelling. The results of the case study of agricultural land cover classification at a regional scale show that using only about a half of the variables we can achieve land cover classification accuracy close to that generated using the full dataset. The proposed simple but effective solution of sample transferring could make supervised modelling possible for applications lacking sample data.
Article
Full-text available
Ground-based whole sky cameras have opened up new opportunities for monitoring the earth's atmosphere. These cameras are an important complement to satellite images by providing geoscientists with cheaper, faster, and more localized data. The images captured by whole sky imagers can have high spatial and temporal resolution, which is an important pre-requisite for applications such as solar energy modeling, cloud attenuation analysis, local weather prediction, etc. Extracting valuable information from the huge amount of image data by detecting and analyzing the various entities in these images is challenging. However, powerful machine learning techniques have become available to aid with the image analysis. This article provides a detailed walk-through of recent developments in these techniques and their applications in ground-based imaging. We aim to bridge the gap between computer vision and remote sensing with the help of illustrative examples. We demonstrate the advantages of using machine learning techniques in ground-based image analysis via three primary applications -- segmentation, classification, and denoising.
Technical Report
Full-text available
This in-depth study was conducted, through an integrated land use planning approach, to explore possible adaptations to climate change (CC) and Sea Level Rise (SLR) of the coastal area of the Vietnamese Mekong Delta (VMD). Based on detailed inventories of the present and anticipated CC and SLR affecting soils, hydrological features and land use, yields and financial returns, a CC adaptation land use strategy for Bac Lieu province has been proposed by applying a Multiple Goal Linear Programming (MGLP) approach. Important impacts of this study are: • Enhanced understanding of the dynamic of inundation (in the rainy season) and salinity intrusion (in the dry season) of the study area in specific and the coastal of the Mekong Delta in general; • Enhanced understanding of the integration between biophysical conditions of the study area (agro-ecological zone) and socio-economic constraints under current condition and future CC and SLR impacts; • Improved knowledge of the current land use issues and opportunity for climate change adaptation; • Developed strategy for CC and SLR adaptation at provincial level (Bac Lieu case study) by applying an integrated land use analysis with guidelines and tools suitable to the Mekong Delta, Vietnam; • Enhanced capacity of local partners and provincial officers on integrated land use planning under the impacts of CC and SLR. • Increased efficiency in using government resources by enhancing knowledge of policy makers on agricultural systems under climate change. To assure the successful of the climate change adaptation strategies, further studies are essential: • Risk management on crop failures (by disease, water pollution, extreme weather) and on market fluctuation. • Soil and water efficiency used (e.g. large-farm model). • Changes of rural labour resources (both quantity and quality) due to migration and mechanization. • Long-term impacts of CC&SLR and additional impacts of land subsidence on salinity and flooding in the Mekong Delta. • Appropriate platform to support innovation practices in the Mekong Delta rural development (financial, manufactory, enterprise, distributor, and farmer innovation…). In order to sustain the development of the VMD's coastal area, an appropriate decision support approach should be developed, in which the natural resources and socio-economic dynamics are interactively considered. Such approach should be able to: • support the participation of different relevant stakeholders in the region and strengthen their capacity in planning and management; • support multi-scales and multi-disciplinary analysis; • consider both spatial and temporal dimensions. Even though there are salinity control systems to protect the salinity intrusion at the coastal area of the VMD, it is still facing with risks of unsustainable development. The area have been dealing with the conflicts between fresh water and brackish water production systems (e.g. rice versus shrimp) and between economic development and environment protection and conservation (shrimp versus forest) at both inside and outside the salinity control area (Ha et al., 2013; Sakamoto et al., 2009; Trung, 2006). The situation would become worse under the impacts of CC and sea level rise (SLR) (Nhan et al., 2011; Smajgl et al., 2015). With changing in natural resources, the life of people in the coastal area would be more vulnerable. This study explores possible adaptation to SLR through land use planning in one case study (Bac Lieu province) in the coastal area of the VMD. Based on detailed inventories of soils, hydrological features and land use, yields and financial returns of different options will be compared. Promising land use systems with new technologies (e.g. new varieties, improved farming techniques), social economic (e.g. labour, revenues) and environmental impacts were taken into account. This case study demonstrates how to involve stakeholders in developing a plan for climate change (CC) adaptation. Theme 5 has completed the following research activities: • Fine mapping of salinity boundary in high spatial and temporal resolution different sections of Bac Lieu province under current and projected sea level and sluice operations. • Fine mapping of soils and current land use in Bac Lieu Province through remote sensing and ground-truth surveys. • Determining the benefits from potential improvement in infrastructure (sluice and dyke system) in terms of salinity and flooding risks of Bac Lieu province. • Analysing biophysical land suitability for rice based land use systems under different sea level rise and infrastructure development scenarios. • Interacting with stakeholder of all levels to identify socio-economic constraints for the adoption of more resilient farming systems and recommend institutional/policy changes. • Applying multiple-goal linear programming for land use planning and define a master plan on climate change adaptation. • Deriving ‗lessons learnt‘ from this case study for future development of adaptation plans in other provinces.
Chapter
Climate change is a critical global issue with the potential to cause social, political, environmental and economic hardships. Women and the poor are disproportionately affected by climate change because of cultural norms, their dependence on natural resources; responsibility for water, fuel, food procurement and household care; their greater exposure to risk in crisis and severe weather events and the predominant presence of low technology in agriculture and their lack of resources and power. This chapter concentrates on vulnerability and adaptation responses at the community level and the context or factors that influence adaptation at this level. In particular, this it focuses gender based vulnerability and adaptation and the factors that influence they respond to climate change. It also highlights the importance of collective adaptation efforts in order to guide the design of more inclusive and effective adaptation projects and programs.
Article
In this study, a multivariable linear algorithm was developed to derive sea surface salinity (SSS) from remote sensing reflectance (Rrs) in the hyper-saline Arabian Gulf. In situ measured Rrs at Operational Land Imager (OLI) bands 1–4 were involved in the algorithm development. Comparisons between estimated and in situ measured SSS produced R²s reaching 0.74 and RMSEs <2%. The proposed algorithm was applied to OLI scenes collected in November 2013 and March 2016 to demonstrate SSS changes from normal conditions when extreme events were encountered. The good agreement between satellite-derived and in situ Rrs suggested that the algorithm uncertainties were primarily attributed to the algorithm parameterization and more measurements were required for performance improving. Compared with OLI-derived products, numerical simulations overestimated SSS by 3.4%. Our findings demonstrate the potential of high resolution satellite products to study short-lasting events and capture fine-scale features in the marine environment.
Article
The main purpose of the present study is to use three state-of-the-art data mining techniques, namely, logistic model tree (LMT), random forest (RF), and classification and regression tree (CART) models, to map landslide susceptibility. Long County was selected as the study area. First, a landslide inventory map was constructed using history reports, interpretation of aerial photographs, and extensive field surveys. A total of 171 landslide locations were identified in the study area. Twelve landslide-related parameters were considered for landslide susceptibility mapping, including slope angle, slope aspect, plan curvature, profile curvature, altitude, NDVI, land use, distance to faults, distance to roads, distance to rivers, lithology, and rainfall. The 171 landslides were randomly separated into two groups with a 70/30 ratio for training and validation purposes, and different ratios of non-landslides to landslides grid cells were used to obtain the highest classification accuracy. The linear support vector machine algorithm (LSVM) was used to evaluate the predictive capability of the 12 landslide conditioning factors. Second, LMT, RF, and CART models were constructed using training data. Finally, the applied models were validated and compared using receiver operating characteristics (ROC), and predictive accuracy (ACC) methods. Overall, all three models exhibit reasonably good performances; the RF model exhibits the highest predictive capability compared with the LMT and CART models. The RF model, with a success rate of 0.837 and a prediction rate of 0.781, is a promising technique for landslide susceptibility mapping. Therefore, these three models are useful tools for spatial prediction of landslide susceptibility.
Article
Several factors can affect the quantity and the quality of groundwater resources, but in coastal aquifers seawater intrusion is often the most significant issue regarding freshwater supply. Further, saltwater intrusion is a worldwide issue because about seventy percent of the world's population lives in coastal regions.
Article
Non-homogeneous regression is often used to statistically post-process ensemble forecasts. Usually only ensemble forecasts of the predictand variable are used as input but other potentially useful information sources are ignored. Although it is straightforward to add further input variables, overfitting can easily deteriorate the forecast performance for increasing numbers of input variables. This paper proposes a boosting algorithm to estimate the regression coefficients while automatically selecting the most relevant input variables by restricting the coefficients of less important variables to zero. A case study with ensemble forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF) shows that this approach effectively selects important input variables to clearly improve minimum and maximum temperature predictions at 5 central European stations.