Inversion of coastal cultivated soil salt content based on multi-source spectra and environmental variables

Soil salinization seriously hinders the development of efficient ecological agriculture in coastal areas. The use of Landsat, Sentinel series and hyperspectral data is an ideal way for assessing soil salinity indicators. However, environmental data (e.g. climate, terrain and parent material) are important factors for estimating such indicators. It is necessary to find the advantages and limitations of a combination of satellite images, hyperspectral data and environmental variables (ENVI) for assessing soil salinity accurately. Various data or their combinations ([I] remote sensing [RS], i.e. bands and salinity indices of Landsat 9 and Sentinel 2; [II] ENVI, including soil attributes, climate and topography; and [III] RS + ENVI) were used to construct the salinity inversion model using random forest (RF) and extremely randomized trees (ERT) for cultivated areas in the coastal plain of Dongtai City, China. The hyperspectral data were also resampled to match the range of the image bands. RF performed better than ERT for all types of analyzed data, and RS + ENVI exhibited the best performance for Sentinel 2 (R² = 0.86). Compared with the RS data alone, Landsat 9 and Sentinel 2 provided higher salinity simulations (41% and 126%, respectively) after combination with ENVI, and salinity mapping was closer to the actual soil salinity measurements. The variables of slope, salinity index (SIT), difference index and SIT had the highest contribution in Landsat 9, Sentinel 2 and resampled hyperspectrum based on Landsat 9 and Sentinel 2, respectively. In conclusion, RS + ENVI based on Sentinel 2 data is the recommended approach for monitoring the salt content of coastal cultivated soil.