Accurate estimation of winter wheat yield under saline stress is crucial for addressing food security challenges and optimizing agricultural management in regional soils. This study proposed a method integrating Sentinel-2 data and field-measured soil salt content (SC) using a random forest (RF) method to improve yield estimation of winter wheat in Kenli County, a typical saline area in China’s Yellow River Delta. First, feature importance analysis of a temporal vegetation index (VI) and salinity index (SI) across all growth periods were achieved to select main parameters. Second, yield models of winter wheat were developed in VI-, SI-, VI + SI-, and VI + SI + SC-based groups. Furthermore, error assessment and spatial yield mapping were analyzed in detail. The results demonstrated that feature importance varied by growth periods. SI dominated in pre-jointing periods, while VI was better in the post-jointing phase. The VI + SI + SC-based model achieved better accuracy (R2 = 0.78, RMSE = 720.16 kg/ha) than VI-based (R2 = 0.71), SI-based (R2 = 0.69), and VI + SI-based (R2 = 0.77) models. Error analysis results suggested that the residuals were reduced as the input parameters increased, and the VI + SI + SC-based model showed a good consistency with the field-measured yields. The spatial distribution of winter wheat yield using the VI + SI + SC-based model showed significant differences, and average yields in no, slight, moderate, and severe salinity areas were 7945, 7258, 5217, and 4707 kg/ha, respectively. This study can provide a reference for winter wheat yield estimation and crop production improvement in saline regions.
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.