A UAV-Based Salt Stress Response Index for Comparative Evaluation of Salinity-Management Interventions in Maize and Soybean

UAV multispectral remote sensing provides an efficient approach for monitoring crop salt stress in saline farmland. This study investigated maize and soybean grown under different salinity-management practices in a coastal saline region. The experiment was conducted at a single site during one growing season, including 14 maize plots and 13 soybean plots with three sampling sites per plot. A Salt Stress Response Index (SSRI) was developed using partial least squares path modeling (PLS-PM) based on baseline soil salinity and four crop growth indicators: leaf area index, plant height, SPAD, and fractional vegetation cover. Boruta was used for vegetation-index selection, and four regression algorithms (PLSR, EN, RF, and GPR) were evaluated for UAV-based SSRI retrieval using leave-one-plot-out cross-validation. SSRI was significantly and negatively correlated with crop yield across growth stages (r = −0.670 to −0.764), supporting its relevance as an integrated indicator of crop stress response. Linear models generally outperformed nonlinear models. EN performed best for maize at the jointing stage (R2 = 0.774, RMSE = 0.124, RPD = 2.103) and soybean at the branching stage (R2 = 0.737, RMSE = 0.131, RPD = 1.952), whereas PLSR performed best for maize and soybean at flowering (R2 = 0.819 and 0.803, respectively). UAV-derived SSRI maps captured within-field spatial heterogeneity, and baseline-salinity-adjusted SSRI enabled exploratory comparison among management practices within the same crop and growth stage. The proposed framework provides a proof-of-concept approach for UAV-based crop salt stress monitoring and exploratory assessment of management responses in saline agricultural systems.