Accurate monitoring of farmland water status is critical for improving water resource use efficiency and enhancing agricultural system resilience. Monitoring either soil moisture content or plant water content alone fails to reveal the overall water status of the farmland system constituted by soil water and plant water. To address this limitation, the present study focuses on maize and employs unmanned aerial vehicle (UAV)-based multispectral imagery acquired during four key growth stages in 2023. Using the coefficient of variation (CV) method and the entropy weight method (EWM), soil moisture and plant water status were integrated to construct a composite moisture index (CMI) capable of quantifying the relationship between soil water supply capacity and plant water deficit, thereby reflecting the overall water stress level of the farmland system. A comparative analysis was conducted on the performance of CMI inversion models driven by UAV data and constructed using machine learning algorithms. The results demonstrated the following: (1) Compared with single growth indicators, the CMI exhibited significantly stronger correlations with spectral indices, indicating its effectiveness in characterizing the overall water status of the farmland system. (2) The proposed model optimization method (SSA-RFE-XGBoost) achieved the highest accuracy across all growth stages from jointing to milking, with R² values ranging from 0.511 to 0.714. (3) The spatiotemporal distribution maps of CMI generated by this model revealed, for the first time, the fine‑scale spatiotemporal variability of system‑level water status in drip‑irrigated maize farmland from the jointing to the milking stage. In summary, this study proposes a comprehensive water estimation model for monitoring the soil–vegetation system, advancing the assessment of farmland water status from single‑medium moisture monitoring to the characterization of soil–plant system water conditions. This provides new methodological support for smart irrigation and sustainable agricultural development in arid regions.