Retrieval of soil salinity based on multi-source remote sensing data and differential transformation technology

ABSTRACT Rapid and accurate assessments of soil salinity information surrounding saline lakes are crucial for agricultural development and ecological security in arid regions. The Support Vector Machine (SVM) algorithm is currently utilized to derive the relationship between environmental covariates and soil salinity to perform remote sensing inversion of regional soil salinity; however, there is still potential for improvement in the existing SVM algorithm. Therefore, this study aims to improve the remote sensing-based soil salinity content (SSC) extraction from the Landsat 8, DEM and HJ-1A CCD satellite data using the Cuckoo Search Algorithms-Support Vector Machines (CS-SVM) model. In addition, the correlation and principal component analysis were conducted to determine the principal components of environmental covariates. The results show that the differential transformation effectively separates the land and water, which helps to reduce the noise in the raw remote sensing image. The analysis of soil and vegetation factors shows that the first three principal components cumulative variance contributed 99.69% on the raw remote sensing image, while the first two principal components cumulative variance contributed 88.01% and 85.28% on the first- and second-order differential transformation remote sensing images, respectively. Interestingly, L-S2 is the only factor correlated with SSC in the third order differential transform remote sensing image, with the R value of 0.325. The slope direction and plane curvature under the topographic factors had negative correlations with SSC, with the R values of −0.521 and −0.325, respectively. Finally, the SSC inversion model was developed using the first order differential transformation remote sensing images, which has high accuracy and good stability (R2 = 0.68 and RMSE = 3.80 g−1). The cuckoo algorithm is helpful for determining the best support vector machine parameters and offers new perspectives in improving the reliability of remote sensing-based soil salinity inversion in arid regions.

[1]  K. Tansey,et al.  Identification of saline landscapes from an integrated SVM approach from a novel 3-D classification schema using Sentinel-1 dual-polarized SAR data , 2022, Remote Sensing of Environment.

[2]  Chun Yan,et al.  Fault diagnosis model of rolling bearing based on parameter adaptive AVMD algorithm , 2022, Applied Intelligence.

[3]  N. Acir,et al.  Soil salinity assessment of a natural pasture using remote sensing techniques in central Anatolia, Turkey , 2022, PloS one.

[4]  Imran Sarwar Bajwa,et al.  Internet of things (IoT) assisted soil salinity mapping at irrigation schema level , 2022, Applied Water Science.

[5]  N. Al‐Ansari,et al.  Prediction of irrigation water quality indices based on machine learning and regression models , 2022, Applied Water Science.

[6]  Xinyue Cao,et al.  Digital soil mapping of soil total nitrogen based on Landsat 8, Sentinel 2, and WorldView-2 images in smallholder farms in Yellow River Basin, China , 2022, Environmental Monitoring and Assessment.

[7]  Lihui Cen,et al.  A novel cause analysis approach of grey reasoning Petri net based on matrix operations , 2021, Appl. Intell..

[8]  Taha Gorji,et al.  Assessing the performance of machine learning algorithms for soil salinity mapping in Google Earth Engine Platform using Sentinel-2A and Landsat-8 OLI data , 2021, Advances in Space Research.

[9]  Zheng Wang,et al.  Regional suitability prediction of soil salinization based on remote-sensing derivatives and optimal spectral index. , 2021, The Science of the total environment.

[10]  Junrui Zhang,et al.  Estimating soil salinity with different fractional vegetation cover using remote sensing , 2020, Land Degradation & Development.

[11]  Ming Men,et al.  Accuracy analysis of remote sensing index enhancement for SVM salt inversion model , 2020, Geocarto International.

[12]  Yishan Wang,et al.  Quantitative Evaluation of Spatial and Temporal Variation of Soil Salinization Risk Using GIS-Based Geostatistical Method , 2020, Remote. Sens..

[13]  Hazem T. Abd El-Hamid,et al.  Hyperspectral remote sensing for extraction of soil salinization in the northern region of Ningxia , 2020, Modeling Earth Systems and Environment.

[14]  D. Rycroft,et al.  Soil salinity , 2020, Modern Land Drainage.

[15]  J. Araus,et al.  Vegetation indices derived from digital images and stable carbon and nitrogen isotope signatures as indicators of date palm performance under salinity , 2020 .

[16]  A. Paz,et al.  Prediction of soil salinity and sodicity using electromagnetic conductivity imaging , 2020 .

[17]  Fei Yang,et al.  Salinization information extraction model based on VI–SI feature space combinations in the Yellow River Delta based on Landsat 8 OLI image , 2019, Geomatics, Natural Hazards and Risk.

[18]  Wei Yang,et al.  Comparison of machine learning algorithms for soil salinity predictions in three dryland oases located in Xinjiang Uyghur Autonomous Region (XJUAR) of China , 2019, European Journal of Remote Sensing.

[19]  M. Hasanlou,et al.  Retrieval of soil salinity from Sentinel-2 multispectral imagery , 2019, European Journal of Remote Sensing.

[20]  G. Buttafuoco,et al.  A geostatistical Vis-NIR spectroscopy index to assess the incipient soil salinization in the Neretva River valley, Croatia , 2018, Geoderma.

[21]  Hong Shu,et al.  Optical remote-sensing data based research on detecting soil salinity at different depth in an arid-area oasis, Xinjiang, China , 2018, Earth Science Informatics.

[22]  Harm Bartholomeus,et al.  Soil salinity assessment through satellite thermography for different irrigated and rainfed crops , 2018, International Journal of Applied Earth Observation and Geoinformation.

[23]  Sina Keller,et al.  Fusion of Hyper Spectral and Ground Penetrating Radar Data to Estimate Soil Moisture , 2018, 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[24]  J. Gamon,et al.  Remote sensing of biodiversity: Soil correction and data dimension reduction methods improve assessment of α-diversity (species richness) in prairie ecosystems , 2018 .

[25]  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.

[26]  F. Shabani,et al.  Soil salinity and matric potential interaction on water use, water use efficiency and yield response factor of bean and wheat , 2018, Scientific Reports.

[27]  Manfred F. Buchroithner,et al.  A Case Study of the Forced Invariance Approach for Soil Salinity Estimation in Vegetation-Covered Terrain Using Airborne Hyperspectral Imagery , 2018, ISPRS Int. J. Geo Inf..

[28]  Rongjun Chen,et al.  Cost Forecasting of Substation Projects Based on Cuckoo Search Algorithm and Support Vector Machines , 2018 .

[29]  Tashpolat Tiyip,et al.  Mapping and Modeling of Soil Salinity Using WorldView-2 Data and EM38-KM2 in an Arid Region of the Keriya River, China , 2018 .

[30]  Arnold Bregt,et al.  55-year (1960-2015) spatiotemporal shoreline change analysis using historical DISP and Landsat time series data in Shanghai , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[31]  M. Ebrahimi,et al.  Cuckoo optimization algorithm in optimal water allocation and crop planning under various weather conditions (case study: Qazvin plain, Iran) , 2019, Neural Computing and Applications.

[32]  Biao Huang,et al.  Information extraction and dynamic evaluation of soil salinization with a remote sensing method in a typical county on the Huang-Huai-Hai Plain of China , 2017 .

[33]  S. K. Singh,et al.  Visible-Near Infrared Reflectance Spectroscopy for Rapid Characterization of Salt-Affected Soil in the Indo-Gangetic Plains of Haryana, India , 2017, Journal of the Indian Society of Remote Sensing.

[34]  Houbing Song,et al.  A Cuckoo Search-Support Vector Machine Model for Predicting Dynamic Measurement Errors of Sensors , 2016, IEEE Access.

[35]  Shitong Wang,et al.  A fast leave-one-out cross-validation for SVM-like family , 2016, Neural Computing and Applications.

[36]  Lalit Kumar,et al.  Assessing soil salinity using soil salinity and vegetation indices derived from IKONOS high-spatial resolution imageries: Applications in a date palm dominated region , 2014 .

[37]  Anwar A. Aly,et al.  Impact of Deficit Irrigation on Soil Salinity and Cucumber Yield under Greenhouse Condition in an Arid Environment , 2013 .

[38]  Mourad Lounis,et al.  Remote Sensing Techniques for Salt Affected Soil Mapping: Application to the Oran Region of Algeria , 2012 .

[39]  Ramin Rajabioun,et al.  Cuckoo Optimization Algorithm , 2011, Appl. Soft Comput..

[40]  M. Kovacevic,et al.  Soil type classification and estimation of soil properties using support vector machines , 2010 .

[41]  A. Skidmore,et al.  Leaf Area Index derivation from hyperspectral vegetation indicesand the red edge position , 2009 .

[42]  Yohei Sato,et al.  Assessment of hydrosaline land degradation by using a simple approach of remote sensing indicators , 2005 .

[43]  J. Chen.  Evaluation of Vegetation Indices and a Modified Simple Ratio for Boreal Applications , 1996 .

[44]  Hui Qing Liu,et al.  A feedback based modification of the NDVI to minimize canopy background and atmospheric noise , 1995, IEEE Transactions on Geoscience and Remote Sensing.

[45]  A. Karnieli,et al.  Spectral reflectance of biogenic crust developed on desert dune sand along the Israel-Egypt border , 1995 .

[46]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[47]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[48]  L. Babiuk,et al.  Host Responses to Infectious Bovine Rhinotracheitis Virus , 1974, The Journal of Immunology.

[49]  L. Babiuk,et al.  Host responses to infectious bovine rhinotracheitis virus. III. Isolation and immunologic activities of bovine T lymphocytes. , 1974, Journal of immunology.

[50]  N. H. Brogea,et al.  Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density , 2022 .