Estimating and mapping the dynamics of soil salinity under different crop types using Sentinel-2 satellite imagery

Authors: CUI, XIN - Northwest A&f University; HAN, WENTING - Northwest A&f University; Zhang, Huihui; DONG, YUXIN - Northwest A&f University; MA, WEITONG - Northwest A&f University; ZHAI, XUEDONG - Northwest A&f University; ZHANG, LIYUAN - Northwest A&f University; LI, GUANG - Northwest A&f University

Submitted to: Geoderma
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/1/2023
Publication Date: 12/5/2023
Citation: Cui, X., Han, W., Zhang, H., Dong, Y., Ma, W., Zhai, X., Zhang, L., Li, G. 2023. Estimating and mapping the dynamics of soil salinity under different crop types using Sentinel-2 satellite imagery. Geoderma. 440. Article e116738. https://doi.org/10.1016/j.geoderma.2023.116738.
DOI: https://doi.org/10.1016/j.geoderma.2023.116738

Interpretive Summary: Soil salinization is when too much salt builds up in the soil, and it's a big problem because it damages the land, messes with the environment, and makes it tough to grow crops. In this study, we aimed to see how the salt levels in the soil change over time, especially when different plants are growing in the Hetao Irrigation District (HID) in China for two years. We used Sentinel-2 satellite imagery for all sunflowers and maize fields in the area. What we found was that considering the type of crop and when it's growing helped us figure out how salty the soil is. This study not only gives us a better way to understand soil saltiness in the HID but also offers valuable strategies for preventing our soil from server salinization, which is good news for farming and the environment.

Technical Abstract: Soil salinization is one of the main factors contributing to land degradation, affecting ecological equilibrium, environmental health, and the sustainable development of agriculture. This study involved field sampling across the entirety of the Hetao Irrigation District (HID) over four cycles from June to September in 2021 and 2022. Its primary objectives were to assess soil salt content (SSC) variations under diverse time series of vegetation cover and investigate how crop types and different temporal factors influence SSC estimation. Sentinel-2 satellite imagery was used to extract synchronized spectral indices and information regarding crop type distribution. Focused on sunflower and maize fields, this study analyzed the impact of classifying these two crop types and examining four distinct time series on the accuracy of SSC estimation. Five indices were selected as characteristic parameters from a pool of 17 vegetation indices (VIs) and 13 salinity indices (SIs) derived from satellite images. Moreover, three machine learning algorithms were employed to establish SSC estimation models, and the optimal model was then employed to generate spatial distribution maps of SSC for multiple time series within HID. The findings underscored the efficacy of classifying crop types and considering different time series in enhancing the response sensitivity of spectral indices to SSC and improving modeling accuracy. Among the spectral indices, VIs made more contributions to the SSC estimation model than SIs, achieving the highest determination coefficient (R2) of 0.71. The artificial neural network algorithm outperformed the other two machine learning algorithms in terms of accuracy and stability, yielding an optimal R2 of 0.6 and a Root Mean Square Error (RMSE) of 0.08%. This study proposed a modeling and mapping approach that takes into account crop types and various time series, offering valuable insights for the accurate assessment of soil salinization guiding strategies for its prevention and remediation in HID.