A longitudinal analysis of soil salinity changes using remotely sensed imageries

• Published in: Scientific reports Vol. 14; no. 1; p. 10383
• Main Authors: Bandak, Soraya, Movahedi-Naeini, Seyed Alireza, Mehri, Saeed, Lotfata, Aynaz
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 06.05.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/119/995; 639/705/1046; 704/158/2456; 704/172/4081; Agricultural production; Decision making; Decision tree; Desertification; Drainage patterns; Drainage systems; Environmental degradation; Humanities and Social Sciences; Imagery; Land degradation; Land use; Landsat; Moisture index; multidisciplinary; Predictive modeling; Remote sensing; Remote sensing techniques; Salinity; Salinity effects; Salinization; Satellite imagery; Science; Science (multidisciplinary); Sensing techniques; Sodium; Soil analysis; Soil salinity; Soil salinization; Topography; Wetness index; Soil salinization; Predictive modeling; Decision tree; Remote sensing
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-60033-6

Soil salinization threatens agricultural productivity, leading to desertification and land degradation. Given the challenges of conducting labor-intensive and expensive field studies and laboratory analyses on a large scale, recent efforts have focused on leveraging remote sensing techniques to study soil salinity. This study assesses the importance of soil salinity indices’ derived from remotely sensed imagery. Indices derived from Landsat 8 (L8) and Sentinel 2 (S2) imagery are used in Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Decision Tree (DT), and Support Vector Machine (SVR) are associated with the electrical (EC) conductivity of 280 soil samples across 24,000 hectares in Northeast Iran. The results indicated that the DT is the best-performing method (RMSE = 12.25, MAE = 2.15, R 2  = 0.85 using L8 data and RMSE = 10.9, MAE = 2.12, and R 2  = 0.86 using S2 data). Also, the results showed that Multi-resolution Valley Bottom Flatness (MrVBF), moisture index, Topographic Wetness Index (TWI), and Topographic Position Indicator (TPI) are the most important salinity indices. Subsequently, a time series analysis indicated a reduction in salinity and sodium levels in regions with installed drainage networks, underscoring the effectiveness of the drainage system. These findings can assist decision-making about land use and conservation efforts, particularly in regions with high soil salinity.