[Objective] To address the inefficiencies of traditional approaches in monitoring soil moisture content (SMC) and soil organic matter content (SOMC) in saline-alkaline farmlands, this study investigates an estimation method that integrates hyperspectral data with interpretable machine learning. The goal is to establish a theoretical foundation for the rapid acquisition of soil information and quality assessment in the Hetao Plain. [Methods] Ground-based hyperspectral reflectance data and field-measured SMC and SOMC were used as the primary data sources. Spectral data were processed using fractional-order differential (FOD) transformation, and various spectral indices were constructed. Models were developed using partial least squares regression (PLSR), support vector machines (SVM), and random forests (RF). To enhance interpretability, the Shapley Additive Explanations (SHAP) method was employed to evaluate the relative contribution of each variable to the model predictions. [Results] ①Spectral indices derived from the 1.25-order differential transformation showed the highest correlation with SMC and SOMC. In particular, the generalized difference index (GDI) and optimal spectral index (OSI) exhibited the strongest correlations, with coefficients of 0.5054 and 0.6825, respectively. ②The RF model significantly outperformed PLSR and SVM in estimating both SMC and SOMC. For the validation datasets, the RF models achieved R2 values of 0.734 and 0.870, RMSEs of 3.28 and 1.53, and RPDs of 2.07 and 2.43, respectively. ③SHAP analysis indicated that the normalized plane domain index (NPDI) and ratio index (RI) were the most influential variables for the estimation of SMC and SOMC, respectively. The combined contributions of NPDI, OSI, and difference index (DI) to SMC modeling reached 68.58%, while RI, GDI, and NPDI collectively contributed 61.86% to SOMC modeling. [Conclusion] The integration of FOD and spectral indices enhances the utility of hyperspectral data. The RF model demonstrated superior accuracy and robustness in estimating soil properties, while SHAP analysis effectively elucidated the contribution of individual variables. Spectral indices such as NPDI, RI, OSI, and DI played significant roles in modeling SMC and SOMC in saline-alkaline farmland. These findings offer novel insights for high-precision estimation of soil attributes and provide valuable guidance for regional soil management and precision agriculture practices.