18 February 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
High-precision mapping of soybeans, a globally significant oil and protein crop, has long been constrained by the limitations of traditional remote sensing methods, particularly regarding their inefficiency in fusing spatio-temporal information and suboptimal classification accuracy. Consequently, the rigorous demands of modern precision agriculture for crop monitoring have often not been adequately addressed. To address these challenges, a novel hybrid model was developed in this study for soybean identification using multi-temporal remote sensing imagery. This model is built upon an improved three-dimensional (3D) U-Net architecture, which synergistically integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Random Forest (RF) algorithms. This integration enables the effective extraction of multi-level features and subsequent integrated classification. A notable innovation of this research involves the incorporation of the Greenness-Water Content Composite Index (GWCCI) into the feature set. GWCCI quantifies canopy greenness and water status, improving discrimination of soybean phenology. Experimental validation was conducted within the primary soybean production region of Hailun City, Heilongjiang Province. The results demonstrated that the proposed model significantly outperformed 10 baseline methods (including standard 3D U-Net, CNN, and RF) across four key metrics: Overall Accuracy (OA), User Accuracy (UA), F1-score, and Kappa coefficient. Specifically, when benchmarked against a standard 3D U-Net, the developed model exhibited a 3.2% increase in OA, a 9.3% increase in UA, a 2.6% improvement in F1-score, and a 6.4% increase in the Kappa coefficient. These quantitative improvements highlight its enhanced capability in distinguishing soybeans from background crops. Ultimately, this research not only provides a novel methodological framework for precise crop classification but also contributes a viable multi-dimensional feature fusion strategy directly applicable to crop monitoring and intelligent agricultural management.
19 January 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Accurate crop yield estimation is essential for global food security, especially high-resolution mapping that supports field-scale management and detailed yield gap analysis. This study developed a hybrid yield estimation framework, named EnKF-RF (Ensemble Kalman Filter–Random Forest), which coupled data assimilation with a two-stage Random Forest approach. In this framework, Sentinel-2-derived leaf area index (LAI) was first assimilated into the WOFOST model using the EnKF algorithm. A RF-based metamodel (RF_SIM) was then trained to approximate the assimilation process, followed by a second RF model (RF_FIELD) that integrated land surface phenology (LSP), extreme climate indicators, and limited ground observations to estimate crop yield. The proposed framework was applied to maize yield estimating in Jilin Province, China, during 2022-2024. The results showed that EnKF-RF achieved superior performance (R² = 0.476, RMSE = 1565.87 kg/ha, MAE = 1299.42 kg/ha) compared to a standalone Random Forest (R² = 0.394, RMSE = 1685.04 kg/ha, MAE = 1428.69 kg/ha) and the Scalable Crop Yield Mapper (SCYM) approach. Furthermore, the implementation of the metamodel substantially enhanced the efficiency of the EnKF-RF framework, allowing annual maize yield estimation to be achieved within 18 minutes per 10,000 km² in Jilin Province when utilizing Google Earth Engine (GEE). Water availability was identified as the primary driver of interannual yield variability, especially due to spring drought and the co-occurrence of water stress and water-logging during July and August according to the SHapley Additive exPlanations (SHAP). Generally, EnKF-RF provides a scalable and efficient solution for high-resolution maize yield mapping, particularly in data-scarce regions.