Radar remote sensing-based inversion model of soil salt content at different depths under vegetation

• Published in: PeerJ (San Francisco, CA) Vol. 10; p. e13306
• Main Authors: Chen, Yinwen, Du, Yuyan, Yin, Haoyuan, Wang, Huiyun, Chen, Haiying, Li, Xianwen, Zhang, Zhitao, Chen, Junying
• Format: Journal Article
• Language: English
• Published: United States PeerJ, Inc 26.04.2022; PeerJ Inc
• Subjects: Accuracy; Agricultural production; Agricultural Science; Artificial intelligence; Best subset selection; Biogeochemistry; Environmental Impacts; Experiments; Irrigation; Machine learning; Radar; Radar remote sensing; Regression analysis; Remote sensing; Remote Sensing Technology - methods; Salinity; Salinity effects; Salt; Satellites; Sodium Chloride; Sodium Chloride, Dietary; Soil; Soil at different depths; Soil salinity; Soil salt content; Soil Science; Spatial and Geographic Information Science; Support vector machine; Support vector machines; Variables; Vegetation; vegetation coverage; China; Radar remote sensing; vegetation coverage; Best subset selection; Soil salt content; Support vector machine; Soil at different depths
• ISSN: 2167-8359; 2167-8359
• DOI: 10.7717/peerj.13306

Excessive soil salt content (SSC) seriously affects the crop growth and economic benefits in the agricultural production area. Prior research mainly focused on estimating the salinity in the top bare soil rather than in deep soil that is vital to crop growth. For this end, an experiment was carried out in the Hetao Irrigation District, Inner Mongolia, China. In the experiment, the SSC at different depths under vegetation was measured, and the Sentinel-1 radar images were obtained synchronously. The radar backscattering coefficients (VV and VH) were combined to construct multiple indices, whose sensitivity was then analyzed using the best subset selection (BSS). Meanwhile, four most commonly used algorithms, partial least squares regression (PLSR), quantile regression (QR), support vector machine (SVM), and extreme learning machine (ELM), were utilized to construct estimation models of salinity at the depths of 0-10, 10-20, 0-20, 20-40, 0-40, 40-60 and 0-60 cm before and after BSS, respectively. The results showed: (a) radar remote sensing can be used to estimate the salinity in the root zone of vegetation (0-30 cm); (b) after BSS, the correlation coefficients and estimation accuracy of the four monitoring models were all improved significantly; (c) the estimation accuracy of the four regression models was: SVM > QR > ELM > PLSR; and (d) among the seven sampling depths, 10-20 cm was the optimal inversion depth for all the four models, followed by 20-40 and 0-40 cm. Among the four models, SVM was higher in accuracy than the other three at 10-20 cm (R = 0.67, R = 0.12%). These findings can provide valuable guidance for soil salinity monitoring and agricultural production in the arid or semi-arid areas under vegetation.