Work

Estimating soil water content of cotton fields using UAV-based multi-source remote sensing data fusion

Year: 2025

Type: article

Abstract: Accurate soil water content (SWC) estimation is essential for optimizing irrigation strategies in cotton cultivation, especially during the flowering, boll setting, and boll opening stages, when SWC variations critically impact yield and fiber quality. Conventional SWC estimation predominantly relies on single-source remote sensing data, lacking comprehensive consideration of multivariate interactions within the soil-plant-atmosphere continuum and compromising accuracy. This study multidimensionally fused thermal infrared, multispectral, and meteorological data to systematically evaluate machine learning algorithms for improving SWC estimation accuracy. Joint water and nitrogen treatments, including three irrigation regimes and three nitrogen application rates, were conducted in the cotton field. SWC data were collected from six soil depths during critical cotton growth stages, and remote sensing images were also acquired. A multidimensional remote sensing feature set was constructed, containing the crop water stress index (CWSI), normalized difference vegetation index (NDVI), temperature vegetation dryness index (TVDI), and three-dimensional drought index (TDDI). Four machine learning algorithms, i.e., support vector regression (SVR), random forest regression (RFR), gradient boosting decision tree (GBDT) and categorical boosting (CatBoost), were evaluated for their performance in estimating SWC. Results showed that TVDIG,R exhibited the strongest correlation with SWC (r = -0.63 ± 0.04), demonstrating heightened sensitivity at soil depths of 0 - 60 cm (r = -0.68). In addition, the CatBoost model showed superior estimation performance (R² = 0.836 ± 0.039, RMSE = 0.27 ± 0.02%), significantly outperforming other models. Although demonstrating robust generalizability (Pc > 0.75), the model’s robustness decreased with crop maturation and reduced irrigation amount. In conclusion, the accuracy of SWC estimation was enhanced by integrating multidimensional indices with machine learning techniques, and a practical technical framework to support precision irrigation in arid cotton agroecosystems was developed.

Source: Agricultural Water Management

DOI: 10.1016/j.agwat.2025.109996