Efficient and accurate rice identification based on high spatial and temporal resolution remote sensing imagery is essential for achieving precision agriculture and ensuring food security. Semantic segmentation networks in deep learning are an effective solution for crop identification, and they are mainly based on two architectures: the commonly used convolutional neural network (CNN) architecture and the novel Vision Transformer architecture. Research on crop identification from remote sensing imagery using Vision Transformer has only emerged in recent times, mostly in sub-meter resolution or even higher resolution imagery. Sub-meter resolution images are not suitable for large scale crop identification as they are difficult to obtain. Therefore, studying and analyzing the differences between Vision Transformer and CNN in crop identification in the meter resolution images can validate the generalizability of Vision Transformer and provide new ideas for model selection in crop identification research at large scale. This paper compares the performance of two representative CNN networks (U-Net and DeepLab v3) and a novel Vision Transformer network (Swin Transformer) on rice identification in Sentinel-2 of 10 m resolution. The results show that the three networks have different characteristics: (1) Swin Transformer has the highest rice identification accuracy and good farmland boundary segmentation ability. Although Swin Transformer has the largest number of model parameters, the training time is shorter than DeepLab v3, indicating that Swin Transformer has good computational efficiency. (2) DeepLab v3 also has good accuracy in rice identification. However, the boundaries of the rice fields identified by DeepLab v3 tend to shift towards the upper left corner. (3) U-Net takes the shortest time for both training and prediction and is able to segment the farmland boundaries accurately for correctly identified rice fields. However, U-Net’s accuracy of rice identification is lowest, and rice is easily confused with soybean, corn, sweet potato and cotton in the prediction. The results reveal that the Vision Transformer network has great potential for identifying crops at the country or even global scale.
The accurate identification of rice fields through remote sensing is critical for agricultural monitoring and global food security. While optical and Synthetic Aperture Radar (SAR) data offer complementary advantages for crop mapping—spectral richness from optical imagery and all-weather capabilities from SAR—their integration remains challenging due to heterogeneous data characteristics and environmental variability. This study systematically evaluates three Transformer-based fusion strategies for rice identification: Early Fusion Transformer (EFT), Feature Fusion Transformer (FFT), and Decision Fusion Transformer (DFT), designed to integrate optical-SAR data at the input level, feature level, and decision level, respectively. Experiments conducted in Arkansas, USA—a major rice-producing region with complex agroclimatic conditions—demonstrate that EFT achieves superior performance, with an overall accuracy (OA) of 98.33% and rice-specific Intersection over Union (IoU_rice) of 83.47%, surpassing single-modality baselines (optical: IoU_rice = 75.78%; SAR: IoU_rice = 66.81%) and alternative fusion approaches. The model exhibits exceptional robustness in cloud-obstructed regions and diverse field patterns, effectively balancing precision (90.98%) and recall (90.35%). These results highlight the superiority of early-stage fusion in preserving complementary spectral–structural information, while revealing limitations of delayed integration strategies. Our work advances multi-modal remote sensing methodologies, offering a scalable framework for operational agricultural monitoring in challenging environments.
Geo-parsing, one of the key components of geographical information retrieval, is a process to recognize and geo-locate toponyms mentioned in texts. Such a process can obtain locations contained in toponyms successfully with consistent updating of neural network models and multiple contextual features. The significant offset distance between the geo-parsed locations and the actual occurrence locations still remains. This is because the geo-parsed locations sourced from toponyms in texts always point to the centers of cities, counties, or towns, and cannot directly represent the actual occurrence locations such as factories, farms, and activity areas. Consequently, The significant offset distances between the geo-parsed locations and the actual occurrence locations limit text mining applications in micro-scale geographic discoveries. This research aims at decreasing offset distances of geo-parsed locations by proposing a novel Toponym Correction Method based on satellite Remote Sensing Images (TC-RSI). The TC-RSI method uses satellite remote sensing images to provide extra detailed spatial information that can be associated with the sentence toponym by corresponding attributes. The TC-RSI method was validated in a case study of the forest ecological pattern dataset of An’hui province from visual, statistical, and robustness assessments. The correction results show that the TC-RSI method dramatically decreases the offset distances from about 50 km to about 1 km and promotes geographical discoveries on smaller scales. A series of analyses indicated that the TC-RSI is a valid, effective, and promising method to improve the accuracy of geo-parsed locations, which allows text mining to find more accurate geographical discoveries with lower offset distances. Moreover, toponym correction promotes the use of more diverse spatial data sources, such as Lidar, domain gazetteers, Wikimedia, and streetscapes, which are expected to usher in a new era of geo-parsing with toponym corrections.