With the rapid development of digital intelligent agriculture, the accurate extraction of field information from remote sensing imagery to guide agricultural planning has become an important issue. In order to better extract fields, we analyze the scale characteristics of agricultural fields and incorporate the multi-scale idea into a Transformer. We subsequently propose an improved deep learning method named the Multi-Swin Mask Transformer (MSMTransformer), which is based on Mask2Former (an end-to-end instance segmentation framework). In order to prove the capability and effectiveness of our method, the iFLYTEK Challenge 2021 Cultivated Land Extraction competition dataset is used and the results are compared with Mask R-CNN, HTC, Mask2Former, etc. The experimental results show that the network has excellent performance, achieving a bbox_AP50 score of 0.749 and a segm_AP50 score of 0.758. Through comparative experiments, it is shown that the MSMTransformer network achieves the optimal values in all the COCO segmentation indexes, and can effectively alleviate the overlapping problem caused by the end-to-end instance segmentation network in dense scenes.

Semantic segmentation is a critical process in remote sensing image analysis, supporting various applications. The recent development of the Segment Anything Model (SAM), a visual foundation model designed to segment-anything, highlights the potential of foundational models in computer vision. However, SAM generates segmentation results without category labels, and predictions from semantic segmentation models for remote sensing often exhibit excessive fragmentation and imprecise boundaries. To address these limitations, we propose a strategy that integrates SAM with semantic segmentation models, replacing the imprecise boundaries of remote sensing segmentation masks with the more boundary-accurate SAM masks while retaining the original semantic information. Subsequently, a framework is designed and realized to enhance the prediction results of semantic segmentation models for remote sensing imagery by leveraging the raw outputs generated by SAM. This approach requires no additional training, modification to the semantic segmentation model, or changes to the visual foundation model, making it efficient and straightforward compared to other methods. Specifically, experimental results on two well-known datasets, LoveDA Urban and ISPRS Potsdam, demonstrate the effectiveness and broad applicability of our approach. Additionally, incorporating recent visual foundation models, such as SAM-HQ and Semantic SAM, further improves segmentation accuracy. As these models advance, the potential of our framework to enhance the performance of semantic segmentation for remote sensing imagery will grow. The source code for this work will be accessible at SESSRS.

Satellite-derived aerosol optical depth (AOD) products from MODIS and VIIRS sensors are vital for monitoring global aerosol distributions. However, inconsistencies in quality control algorithms and spatial resolution introduce errors that complicate validation processes and reduce the accuracy of satellite-to-ground comparisons. This study proposes the “optimal” spatial matching method to minimize these errors and enable a more accurate evaluation of retrieval algorithm performance. Using AERONET ground observations from 2012 to 2021, MODIS and VIIRS AOD products were systematically validated with three spatial matching methods—“direct”, “average”, and “optimal”. Results demonstrate that the “optimal” method consistently outperformed the other methods by selecting pixel values. The study highlights significant quality control disparities across AOD products and demonstrates that high-resolution products, with purer pixels, achieve superior accuracy under the “optimal” method. These insights provide valuable guidance for optimizing dataset applications and refining aerosol retrieval algorithms.

Long time series of annual land cover with fine spatio-temporal resolutions play a crucial role in studying environmental climate change, biophysical modeling, carbon cycling models, and land management. Despite a strong consistency exhibited by several publicly available medium to fine resolution global land cover datasets, significant discrepancies exist at the regional scale; moreover, only every 5/10 year land cover were available. Consequently, high-quality annual land cover datasets before 2000 are unavailable in China. In this study, we proposed a deep learning-based method by integrating multiple remote sensing data from different platforms with historical high spatial resolution land cover datasets (CNLUCC) to derive the 30 m annual land cover maps from 1980 to 1990 for Qilian Mountain. First, the super-resolution generative adversarial network models for upscaling the 5.5 km AVHRR NDVI to 250 m were established by employing the AVHRR and MODIS NDVI data with the same year as input, and the early time series AVHRR NDVI data were subsequently upscaled to 250 m through the above models. Second, the breaks for the additive seasonal and trend (BFAST) change detection algorithm was applied to the upscaled time series NDVI data to detect the change time of different land cover types. Third, the CNLUCC data in 1980 and 1990 were updated to annual land cover datasets from 1980 to 1990 and the annual mapping results provided insights into the dynamic processes of urbanization, deforestation, water bodies, and farmland from 1980 to 1990. Finally, comprehensive analysis and validation were carried out for evaluation and an overall accuracy of 77.26% for the land cover product in 1986 was achieved.

High accuracy and time synchronous aerosol optical depth (AOD) is essential for atmospheric correction (AC) of medium and high spatial resolution (MHSR) remote sensing data. However, existing high-resolution AOD retrieval methods often rely on sparsely distributed ground-based measurements, which limits their capacity to resolve fine-scale spatial heterogeneity and consequently constrains retrieval performance. To address this limitation, we propose a framework that takes GF-1 top-of-atmosphere (TOA) reflectance as input, where the model is first pre-trained using MCD19A2 as Pseudo-labels, with high-confidence samples weighted according to their spatial consistency and temporal stability, and then fine-tuned using Aerosol Robotic Network (AERONET) observations. This approach enables improved retrieval accuracy while better capturing surface variability. Validation across multiple regions demonstrates strong agreement with AOD measurements, achieving the correlation coefficient (R) of 0.941 and RMSE of 0.113. Compared to models without pretraining, the proportion of AOD retrievals within EE improves by 13%. While applied to AC, the corrected surface reflectance also shows strong consistency with in situ observations (R > 0.93, RMSE < 0.04). The proposed Trans-AODnet significantly enhances the accuracy and reliability of AOD inputs for AC of high-resolution wide-field sensors (e.g., GF-WFV), offering robust support for regional environmental monitoring and exhibiting strong potential for broader remote sensing applications.