Rice is one of the world’s most important food crops, feeding over half of the global population and being crucial for food security. Accurate, timely mapping of rice fields is essential for precision agriculture, yet conventional methods relying on static samples fail to capture dynamic farmers’ planting decisions. To address this, we propose the Multi-Source Dynamic Sample Generation and Phenology-Guided Feature Selection Framework for In-Season Rice Identification (MSDF-RiceID) using multi-source remote sensing imagery. It incorporates two key innovations: (i) a rule-based sample updating mechanism based on historical rice maps and a dynamic threshold algorithm, and (ii) phenology-guided feature optimization through exponential weighting. Developed specifically to handle complex cropping patterns and high cloud cover in Hunan Province, MSDF-RiceID integrates these innovations within a grid-search-optimized Random Forest classifier to produce reliable monthly rice distribution maps. In-season samples corresponding to transplanting dates in April (DOY 100, 120), June (DOY 160), and July (DOY 184), differentiated as early-, middle-, and late-rice crops. The optimal feature set combined Sentinel-1 (PRI, VH, VH_VV), Sentinel-2 (NDYI, PSRI, NDBI, NDWI), and MODIS (NDVI, EVI, NDBI, LSWI) indices. Accuracy increased seasonally, with F1-score rising from 0.82 in May to 0.97 at harvest. Cross-region validation in Taishan (Guangdong) and Panjin (Liaoning) showed that the earliest identifiable stage (F1-score > 0.9) occurred earlier than in Hunan due to Hunan’s more complex triple-cropping phenology, highlighting the model’s strong transferability. Furthermore, MSDF-RiceID outperformed existing products (TWDTW-Rice and EARice10), increasing overall accuracy by 0.12–0.18, Kappa by 0.23–0.35, and F1-score by 0.09–0.15. These results demonstrate its effectiveness for in-season, large-scale, and dynamic rice mapping under persistent cloud cover, thereby providing direct support for precision agricultural management in heterogeneous cropping systems.

Rice sustains 18% of the global population on merely 7% of arable land, making accurate rice mapping critical to ensure food security in China. Synthetic Aperture Radar (SAR), with minimal weather dependence, enables continuous rice monitoring in cloud-prone regions. However, existing SAR-based methods require prior phenological knowledge or extensive training samples, limiting their scalability. To address this limitation, we propose Rice-SamPheno—an automated method utilizing time-series Sentinel-1 data, generating rice samples with implicit phenological information. This method characterizes rice backscatter dynamics across growth stages, particularly capturing backscatter variations across geographical regions. The dynamic threshold (DT) algorithm—our core innovation—enables a breakthrough in rice sample generation through self-adaptation to regional agronomic variations including transplanting timing, growth duration, and single/double rice rotation patterns. This process produces spatially explicit, phenology-labeled samples at large scale, with the combination of spectral similarity measures (SSM) and adaptive optimal threshold estimation dynamically refining rice classification thresholds. Validation across three agroecological zones demonstrated post-masking accuracies of 95.78% (Taishan, Guangdong), 90.68% (Nanchang, Jiangxi), and 94.87% (Fujin, Heilongjiang). Pre-masking results (85.94% in Jiangxi) revealed that aquatic vegetation interference was mitigated by farmland masking (Esri 2020 dataset). Crucially, algorithmically generated samples covering heterogeneous cropping systems enabled 3.53% higher rice mapping accuracy than field surveys in Jiangxi. The adaptive optimal threshold method achieved near-identical accuracy (<0.2% deviation) to manual thresholds, while overcoming region-specific limitations. These advancements establish Rice-SamPheno as a scalable solution for cloud-affected regions, offering phenological priors and high-confidence training samples for global rice monitoring in data-scarce environments.