Timely and accurate information on rice cultivation makes important contributions to the profound reform of the global food and agricultural system, and promotes the development of global sustainable agriculture. With all-day and all-weather observing ability, synthetic aperture radar (SAR) can monitor the distribution of rice in tropical and subtropical areas. To solve the problem of misclassification of rice with no marked signal during the flooding period in subtropical hilly areas, this paper proposes a new feature combination and dual branch bi-directional long short-term memory (DB-BiLSTM) model to achieve high-precision rice mapping using Sentinel-1 time series data. Based on field investigation data, the backscatter time series curves of the rice area were analyzed, and a characteristic index (VV − VH)/(VV + VH) (VV: vertical emission and vertical receipt of polarization, VH: vertical emission and horizontal receipt of polarization) for small areas of hilly land was proposed to effectively distinguish rice and non-rice crops with no marked flooding period. The DB-BiLSTM model was designed, ensuring the independent learning of multiple features and effectively combining the time series information of both (VV − VH)/(VV + VH) and VH features. The city of Shanwei, Guangdong Province, China, was selected as the study area. Experimental results showed that the overall accuracy of the rice mapping results was 97.29%, and the kappa coefficient reached 0.9424. Compared to other methods, the rice mapping results obtained by the proposed method maintained good integrity and had less misclassification, which demonstrated the proposed method’s practical value in accurate and effective rice mapping tasks.

The mapping of water surfaces is important for water resource and flood monitoring. Synthetic Aperture Radar (SAR) images can be used to monitor water bodies and detect floods over large areas. To address the problem of low identification accuracy in different time phases and different scales of water area, a water surface mapping method based on Attention-UNet3+ with SAR images is proposed in this paper. In the model, full-scale skip connections are introduced for combining feature maps from different scales and improving the accuracy of narrow water identification; the spatial attention module is used to obtain the importance of each connected feature, which can reduce the number of false alarms caused by speckle noise and water shadows in SAR data; the deep supervision module is used to learn hierarchical representative features from comprehensive aggregated feature maps to provide the periodic output capability of the model and meet the needs of rapid and large-scale water identification. The effectiveness of Attention-UNet3+ is verified by experiments in the Poyang Lake region with Sentinel-1 SAR images. The results show that the proposed Attention-UNet3+ outperforms the conventional threshold segmentation and deep learning models such as UNet, Deepvlabv3+, and SegNet, with an average IOU/Kappa value of 0.9502/0.9698. Multitemporal Sentinel-1 images in 2021 covering Poyang Lake are used for time series water surface mapping with the proposed method, and it is found that the detected water area of Poyang Lake has a good correlation with the corresponding water level values at observation stations. The Pearson coefficients are about 0.96. The above results indicate that the proposed method achieves good water surface mapping performance.

The scattering features of objects in synthetic aperture radar (SAR) imagery are highly sensitive to different azimuth angles, and detecting azimuth-sensitive objects in complex scenes becomes a challenging task. To address this issue, we propose a novel framework called the spatial orientation attention enhancement network (SOAEN) by using aircraft detection in complex scenes of SAR imagery as a case study. Taking YOLOX as the basic framework, this framework introduces the inverted pyramid ConvMixer network (IPCN), the spatial-orientation-enhanced path aggregation feature pyramid network (SOEPAFPN), and the anchor-free decoupled head (AFDH) to achieve performance improvement. A spatial orientation attention module is proposed and introduced into the path aggregation feature pyramid network to form a new structure, the SOEPAFPN, for capturing feature transformations in different directions, highlighting object features and suppressing background effects; the IPCN is adapted to replace the backbone network of YOLOX for enhancing the multiscale feature extraction capability and reducing the computational complexity, while the AFDH is used to decouple object localization and classification to improve the efficiency and accuracy of object localization and classification. The experimental results of the multiple real complex scenes on Gaofen-3 1 m images show that the proposed method achieves the highest detection accuracy, with an average detection rate of 91.22% compared with the YOLO series networks.

Reliable and timely rice distribution information is of great value for real-time, quantitative, and localized control of rice production information. Synthetic aperture radar (SAR) has all-weather and all-day observation capability to monitor rice distribution in tropical and subtropical areas. To improve the physical interpretability and spatial interpretability of the deep learning model for SAR rice field extraction, a new SHapley Additive exPlanation (SHAP) value-guided explanation model (SGEM) for polarimetric SAR (PolSAR) data was proposed. First, a rice sample set was produced based on field survey and optical data, and the physical characteristics were extracted using decomposition of polarimetric scattering. Then a SHAP-based Physical Feature Interpretable Module (SPFIM) combing the long short-term memory (LSTM) model and SHAP values was designed to analyze the importance of physical characteristics, a credible physical interpretation associated with rice phenology was provided, and the weight of physical interpretation was combined with the weight of original PolSAR data. Moreover, a SHAP-guided spatial interpretation network (SSEN) was constructed to internalize the spatial interpretation values into the network layer to optimize the spatial refinement of the extraction results. Shanwei City, Guangdong Province, China, was chosen as the study area. The experimental results showed that the physical explanation provided by the proposed method had a high correlation with the rice phenology, and spatial self-interpretation for finer extraction results. The overall accuracy of the rice mapping results was 95.73%, and the kappa coefficient reached 0.9143. The proposed method has a high interpretability and practical value compared with other methods.

In recent years, synthetic aperture radar (SAR) has been a widely used data source in the remote sensing field due to its ability to work all day and in all weather conditions. Among SAR satellites, Sentinel-1 is frequently used to monitor large-scale ground objects. The Mekong Delta is a major agricultural region in Southeast Asia, so monitoring its cropland is of great importance. However, it is a challenge to distinguish cropland from other ground objects, such as aquaculture and wetland, in this region. To address this problem, the study proposes a statistical feature combination from the Sentinel-1 dual-polarimetric (dual-pol) data time series based on the m/χ decomposition method. Then the feature combination is put into the proposed Omni-dimensional Dynamic Convolution Residual Segmentation Model (ODCRS Model) of high fitting speed and classification accuracy to realize the cropland extraction of the Mekong Delta region. Experiments show that the ODCRS model achieves an overall accuracy of 93.85%, a MIoU of 88.04%, and a MPA of 93.70%. The extraction results show that our method can effectively distinguish cropland from aquaculture areas and wetlands.

Tropical and subtropical Asia is the major rice-producing region in the world, but the complexity of the cropping system and the diversity of the topography bring challenges to the accurate monitoring of rice cultivation. To address this difficulty, a new deep learning model, ESF-Seg, is proposed in this study to extract the annual tropical rice distribution using monthly averaged time-series Sentinel-1 VH data. The ESF-Seg adopts the Efficient Adaptive Sparse Transformer (EAT) to remove redundant information from input features. The Channel Attention Bridge Block (CAB) and Spatial Attention Bridge Block (SAB) modules are introduced to refine the information. Meanwhile, with the FreqFusion-KAN (FreqK) module, the loss of information can be reduced through the multi-scale feature fusion strategy. The proposed method is evaluated in the Hainan Province of China, an important tropical arable zone with diverse crop resources and complicated croplands. First, ablation experiments are conducted. Compared to the classical SegFormer model, the ESF-Seg model improves on the mIOU by 4.99% and on the mPA by 2.65%. Subsequently, compared to the RF, U-Net, and the original SegFormer model, the overall accuracy (OA) of the ESF-Seg model on the validation samples increased by 11.02%, 2.01%, and 1.33%, and the F1 score improved by 0.0756, 0.0624, and 0.0490, reaching 98.31% and 0.9506, respectively. Furthermore, products showing the annual rice distribution from 2019 to 2023 in Hainan are generated, which exhibit good alignments with the statistical data, surpassing other existing products with an RMSE of 5.4004 Kha. As indicated by the rice mapping products, the proposed method preserves the integrity of the rice parcels in the fragmented croplands, thus providing a new opportunity for the continuous monitoring of tropical rice distribution with high accuracy.