Integrating Remote Sensing and Landscape Characteristics to Estimate Soil Salinity Using Machine Learning Methods: A Case Study from Southern Xinjiang, China

Soil salinization, one of the most severe global land degradation problems, leads to the loss of arable land and declines in crop yields. Monitoring the distribution of salinized soil and degree of salinization is critical for management, remediation, and utilization of salinized soil; however, there is a lack of thorough assessment of various data sources including remote sensing and landscape characteristics for estimating soil salinity in arid and semi-arid areas. The overall goal of this study was to develop a framework for estimating soil salinity in diverse landscapes by fusing information from satellite images, landscape characteristics, and appropriate machine learning models. To explore the spatial distribution of soil salinity in southern Xinjiang, China, as a case study, we obtained 151 soil samples in a field campaign, which were analyzed in laboratory for soil electrical conductivity. A total of 35 indices including remote sensing classifiers (11), terrain attributes (3), vegetation spectral indices (8), and salinity spectral indices (13) were calculated or derived and correlated with soil salinity. Nine were used to model and estimate soil salinity using four predictive modelling approaches: partial least squares regression (PLSR), convolutional neural network (CNN), support vector machine (SVM) learning, and random forest (RF). Testing datasets were divided into vegetation-covered and bare soil samples and were used for accuracy assessment. The RF model was the best regression model in this study, with R2 = 0.75, and was most effective in revealing the spatial characteristics of salt distribution. Importance analysis and path modeling of independent variables indicated that environmental factors and soil salinity indices including digital elevation model (DEM), B10, and green atmospherically resistant vegetation index (GARI) showed the strongest contribution in soil salinity estimation. This showed a great promise in the measurement and monitoring of soil salinity in arid and semi-arid areas from the integration of remote sensing, landscape characteristics, and using machine learning model.

[1]  Jingwei Wu,et al.  Comparison of partial least square regression, support vector machine, and deep-learning techniques for estimating soil salinity from hyperspectral data , 2018 .

[2]  Zhou Shi,et al.  Fine-Resolution Mapping of Soil Total Nitrogen across China Based on Weighted Model Averaging , 2019, Remote. Sens..

[3]  Xiaohang Li,et al.  Capability of Sentinel-2 MSI data for monitoring and mapping of soil salinity in dry and wet seasons in the Ebinur Lake region, Xinjiang, China , 2019, Geoderma.

[4]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[5]  Hao Yu,et al.  Mapping Soil Salinity/Sodicity by using Landsat OLI Imagery and PLSR Algorithm over Semiarid West Jilin Province, China , 2018, Sensors.

[6]  Zhou Shi,et al.  Characterising dryland salinity in three dimensions. , 2019, The Science of the total environment.

[7]  Mahdi Hasanlou,et al.  Soil salinity mapping using dual-polarized SAR Sentinel-1 imagery , 2018, International Journal of Remote Sensing.

[8]  D. Politis,et al.  Bootstrap prediction intervals for linear, nonlinear, and nonparametric autoregressions , 2016 .

[9]  C. Siebe,et al.  Mapping soil salinity using a combined spectral response index for bare soil and vegetation: A case study in the former lake Texcoco, Mexico , 2006 .

[10]  Brian Alan Johnson,et al.  Machine-learning classification of debris-covered glaciers using a combination of Sentinel-1/-2 (SAR/optical), Landsat 8 (thermal) and digital elevation data , 2020, Geomorphology.

[11]  K. S. Hari Prasad,et al.  Estimation of water cloud model vegetation parameters using a genetic algorithm , 2012 .

[12]  Jianli Ding,et al.  Estimation of soil salt content (SSC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, based on a Bootstrap-BP neural network model and optimal spectral indices. , 2018, The Science of the total environment.

[13]  Cuizhen Wang,et al.  Mapping Soil Alkalinity and Salinity in Northern Songnen Plain, China with the HJ-1 Hyperspectral Imager Data and Partial Least Squares Regression , 2018, Sensors.

[14]  Jian-Li Ding,et al.  A WFS-SVM Model for Soil Salinity Mapping in Keriya Oasis, Northwestern China Using Polarimetric Decomposition and Fully PolSAR Data , 2018, Remote. Sens..

[15]  E. Muller,et al.  Modeling soil moisture-reflectance , 2001 .

[16]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[17]  A. Gitelson,et al.  Use of a green channel in remote sensing of global vegetation from EOS- MODIS , 1996 .

[18]  Ioannis K. Tsanis,et al.  Assessing soil salinity using WorldView-2 multispectral images in Timpaki, Crete, Greece , 2018 .

[19]  Pratyush Nidhi Sharma,et al.  Model selection uncertainty and multimodel inference in partial least squares structural equation modeling (PLS-SEM) , 2020 .

[20]  Zhou Shi,et al.  Assessing Reclamation Levels of Coastal Saline Lands with Integrated Stepwise Discriminant Analysis and Laboratory Hyperspectral Data , 2006 .

[21]  Guangping Liu,et al.  Soil salinity prediction and mapping by machine learning regression in Central Mesopotamia, Iraq , 2018, Land Degradation & Development.

[22]  Mohammad Ali Ghorbani,et al.  Spatial modeling of soil salinity using multiple linear regression, ordinary kriging and artificial neural network methods , 2017 .

[23]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[24]  Yuanyuan Yang,et al.  Improving TMPA 3B43 V7 Data Sets Using Land-Surface Characteristics and Ground Observations on the Qinghai–Tibet Plateau , 2018, IEEE Geoscience and Remote Sensing Letters.

[25]  Ayad M. Fadhil Al-Quraishi,et al.  Using L-band radar data for soil salinity mapping—a case study in Central Iraq , 2019, Environmental Research Communications.

[26]  Ligang Ma,et al.  Characterizing and modeling regional-scale variations in soil salinity in the arid oasis of Tarim Basin, China , 2017 .

[27]  Carlos Alberto Valera,et al.  The modeling of pasture conservation and of its impact on stream water quality using Partial Least Squares-Path Modeling. , 2019, The Science of the total environment.

[28]  Shengtian Yang,et al.  Multi-algorithm comparison for predicting soil salinity , 2020 .

[29]  Jingyi Huang,et al.  Mapping soil salinity in 3‐dimensions using an EM38 and EM4Soil inversion modelling at the reconnaissance scale in central Morocco , 2017 .

[30]  Weicheng Wu,et al.  Soil Salinity Mapping by Multiscale Remote Sensing in Mesopotamia, Iraq , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  Grace B. Villamor,et al.  Soil salinity assessment and coping strategies in the coastal agricultural landscape in Djilor district, Senegal , 2019, Land Use Policy.

[32]  Zhou Shi,et al.  Assessment and mapping of environmental quality in agricultural soils of Zhejiang Province, China , 2007 .

[33]  V. L. Mulder,et al.  The use of remote sensing in soil and terrain mapping — A review , 2011 .

[34]  N. Goel,et al.  Influences of canopy architecture on relationships between various vegetation indices and LAI and Fpar: A computer simulation , 1994 .

[35]  Biao Huang,et al.  Prediction of soil salinity with soil-reflected spectra: A comparison of two regression methods , 2019, Scientific Reports.

[36]  Yi Wang,et al.  Machine learning-based detection of soil salinity in an arid desert region, Northwest China: A comparison between Landsat-8 OLI and Sentinel-2 MSI. , 2020, The Science of the total environment.

[37]  Christian Walter,et al.  Detecting salinity hazards within a semiarid context by means of combining soil and remote-sensing data , 2006 .

[38]  N. R. Patel,et al.  Satellite-derived vegetation temperature condition index to infer root zone soil moisture in semi-arid province of Rajasthan, India , 2019, Geocarto International.

[39]  Zhou Shi,et al.  Predicting total dissolved salts and soluble ion concentrations in agricultural soils using portable visible near-infrared and mid-infrared spectrometers , 2016 .

[40]  Andrija Krtalić,et al.  Characterization of short-term salinity fluctuations in the Neretva River Delta situated in the southern Adriatic Croatia using Landsat-5 TM , 2020 .

[41]  Jing Wang,et al.  Mapping coastal wetland soil salinity in different seasons using an improved comprehensive land surface factor system , 2019 .

[42]  Hongwei Zheng,et al.  AGA-SVR-based selection of feature subsets and optimization of parameter in regional soil salinization monitoring , 2020 .

[43]  C. Conrad,et al.  Modelling End-of-Season Soil Salinity in Irrigated Agriculture Through Multi-temporal Optical Remote Sensing, Environmental Parameters, and In Situ Information , 2018, PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science.

[44]  Fei Wang,et al.  Quantitative Estimation of Soil Salinity Using UAV-Borne Hyperspectral and Satellite Multispectral Images , 2019, Remote. Sens..

[45]  T. Skaggs,et al.  Regional-scale soil salinity assessment using Landsat ETM + canopy reflectance , 2015 .

[46]  C. Wang,et al.  Comparing Sentinel-2 MSI and Landsat 8 OLI in soil salinity detection: a case study of agricultural lands in coastal North Carolina , 2019, International Journal of Remote Sensing.

[47]  Leung Tsang,et al.  Soil moisture retrieval from time series multi-angular radar data using a dry down constraint , 2019, Remote Sensing of Environment.

[48]  Bernard A. Engel,et al.  Analyzing spatiotemporal characteristics of soil salinity in arid irrigated agro-ecosystems using integrated approaches , 2019 .

[49]  Khaled S. Gemail,et al.  Mapping soil salinity using spectral mixture analysis of landsat 8 OLI images to identify factors influencing salinization in an arid region , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[50]  Florian Schuberth,et al.  Estimating and assessing second-order constructs using PLS-PM: the case of composites of composites , 2020, Ind. Manag. Data Syst..

[51]  J. Huang,et al.  Mapping soil salinity and a fresh-water intrusion in three-dimensions using a quasi-3d joint-inversion of DUALEM-421S and EM34 data. , 2017, The Science of the total environment.

[52]  J. Qi,et al.  Detecting soil salinity with MODIS time series VI data , 2015 .

[53]  Alejandro Cervantes,et al.  Convolution on neural networks for high-frequency trend prediction of cryptocurrency exchange rates using technical indicators , 2020, Expert Syst. Appl..

[54]  Ligang Ma,et al.  Modeling variations in soil salinity in the oasis of Junggar Basin, China , 2018 .

[55]  Wim Turkenburg,et al.  The global technical and economic potential of bioenergy from salt-affected soils , 2011 .

[56]  Shahbaz Khan,et al.  Using Remote Sensing Techniques for Appraisal of Irrigated Soil Salinity , 2007 .

[57]  A. Bannari,et al.  Characterization of Slightly and Moderately Saline and Sodic Soils in Irrigated Agricultural Land using Simulated Data of Advanced Land Imaging (EO‐1) Sensor , 2008 .

[58]  Adriaan van Niekerk,et al.  Machine learning performance for predicting soil salinity using different combinations of geomorphometric covariates , 2017 .

[59]  Ruhollah Taghizadeh-Mehrjardi,et al.  Investigation of the spatial and temporal variation of soil salinity using random forests in the central desert of Iran , 2020, Geoderma.

[60]  T. Skaggs,et al.  Regional scale soil salinity evaluation using Landsat 7, western San Joaquin Valley, California, USA , 2014 .

[61]  Jianli Ding,et al.  Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS–NIR) spectroscopy, Ebinur Lake Wetland, Northwest China , 2018, PeerJ.

[62]  Shaohua Zhao,et al.  Soil Moisture Retrieval from the Chinese GF-3 Satellite and Optical Data over Agricultural Fields , 2018, Sensors.

[63]  Elif Sertel,et al.  Monitoring soil salinity via remote sensing technology under data scarce conditions: A case study from Turkey , 2017 .

[64]  B. He,et al.  Fmask 4.0: Improved cloud and cloud shadow detection in Landsats 4–8 and Sentinel-2 imagery , 2019, Remote Sensing of Environment.

[65]  Budiman Minasny,et al.  Digital mapping of soil salinity in Ardakan region, central Iran , 2014 .

[66]  El Mouatassime Sabri,et al.  Modelling soil salinity in Oued El Abid watershed, Morocco , 2018 .

[67]  N. Baghdadi,et al.  Soil moisture retrieval over irrigated grassland using X-band SAR data , 2016 .

[68]  Elif Sertel,et al.  Soil salinity analysis of Urmia Lake Basin using Landsat-8 OLI and Sentinel-2A based spectral indices and electrical conductivity measurements , 2020 .

[69]  Ren-Min Yang,et al.  Using Sentinel-1 Imagery for Soil Salinity Prediction Under the Condition of Coastal Restoration , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[70]  Simon Beecham,et al.  Soil Salinity Mapping of Urban Greenery Using Remote Sensing and Proximal Sensing Techniques; The Case of Veale Gardens within the Adelaide Parklands , 2018, Sustainability.

[71]  Jianli Ding,et al.  Monitoring and evaluating spatial variability of soil salinity in dry and wet seasons in the Werigan–Kuqa Oasis, China, using remote sensing and electromagnetic induction instruments , 2014 .

[72]  Tien-Dat Pham,et al.  Soil Salinity Mapping Using SAR Sentinel-1 Data and Advanced Machine Learning Algorithms: A Case Study at Ben Tre Province of the Mekong River Delta (Vietnam) , 2019, Remote. Sens..

[73]  L. S. Sanches Fernandes,et al.  A partial least squares - Path modeling analysis for the understanding of biodiversity loss in rural and urban watersheds in Portugal. , 2018, The Science of the total environment.

[74]  Geoffrey S. Hubona,et al.  Using PLS path modeling in new technology research: updated guidelines , 2016, Ind. Manag. Data Syst..

[75]  Arnold K. Bregt,et al.  Global mapping of soil salinity change , 2019, Remote Sensing of Environment.

[76]  Changkun Wang,et al.  Estimating the soil salinity over partially vegetated surfaces from multispectral remote sensing image using non-negative matrix factorization , 2019, Geoderma.

[77]  Zhou Shi,et al.  Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China , 2019, Geoderma.