With the rapid development of the remote sensing monitoring and computer vision technology, the deep learning method has made a great progress to achieve applications such as earth observation, climate change and even space exploration. However, the model trained on existing data cannot be directly used to handle the new remote sensing data, and labeling the new data is also time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) is one of the solutions to the aforementioned problems of labeled data defined as the source domain and unlabeled data as the target domain, i.e., its essential purpose is to obtain a well-trained model and tackle the problem of data distribution discrepancy defined as the domain shift between the source and target domain. There are a lot of reviews that have elaborated on UDA methods based on natural data, but few of these studies take into consideration thorough remote sensing applications and contributions. Thus, in this paper, in order to explore the further progress and development of UDA methods in remote sensing, based on the analysis of the causes of domain shift, a comprehensive review is provided with a fine-grained taxonomy of UDA methods applied for remote sensing data, which includes Generative training, Adversarial training, Self-training and Hybrid training methods, to better assist scholars in understanding remote sensing data and further advance the development of methods. Moreover, remote sensing applications are introduced by a thorough dataset analysis. Meanwhile, we sort out definitions and methodology introductions of partial, open-set and multi-domain UDA, which are more pertinent to real-world remote sensing applications. We can draw the conclusion that UDA methods in the field of remote sensing data are carried out later than those applied in natural images, and due to the domain gap caused by appearance differences, most of methods focus on how to use generative training (GT) methods to improve the model’s performance. Finally, we describe the potential deficiencies and further in-depth insights of UDA in the field of remote sensing.
Satellite image sequence prediction, which supports critical applications in disaster prevention and environmental monitoring, remains challenging due to the detail-rich and long-range chaotic nature of satellite data. Existing data-driven paradigms-whether recurrent or non-recurrent-struggle to effectively capture both short- and long-term spatiotemporal dynamics. To address this, we design a novel semi-recurrent paradigm that combines parallel input encoding with a recurrent, progressive output mechanism, enabling robust reasoning and prediction for both short and long sequences. In addition, we propose SirP, a new prediction network featuring three key innovations specifically designed for the semi-recurrent paradigm and the characteristics of satellite imagery: a triple-view attention module, an accumulated-and-current feature-based progressive predictor, and a nearest-frame skip connection. Comprehensive experiments on five datasets constructed from Himawari-8, FY- 4B, and GOES-16 satellite observations, covering the coastal East Asia and North American continental regions, show that SirP consistently outperforms state-of-the-art methods from both recurrent and non-recurrent paradigms across pixel-level and event-level metrics, with greater gains as the prediction horizon extends. Detailed ablation studies confirm the effectiveness of each core component. The code will be made publicly available.
Accurate station-level numerical weather predictions are critical for disaster prevention and mitigation, with error correction playing an essential role. However, existing correction models struggle to effectively handle the high-dimensional features and complex dependencies inherent in meteorological data. To address these challenges, this paper proposes the dual-branch residual-guided multi-view attention fusion network (DRAF-Net), a novel deep learning-based correction model. DRAF-Net introduces two key innovations: (1) a dual-branch residual structure that enhances the spatial sensitivity of deep high-dimensional features and improves output stability by connecting raw data and shallow features to deep features, respectively; and (2) a multi-view attention fusion mechanism that models spatiotemporal influences, temporal dynamics, and spatial associations, significantly improving the representation of complex dependencies. The effectiveness of DRAF-Net was validated on two real-world datasets comprising observations and predictions from Chinese meteorological stations. It achieved an average RMSE reduction of 83.44% and an average MAE reduction of 84.21% across all eight variables, significantly outperforming other methods. Moreover, extensive studies confirmed the critical contributions of each key component, while visualization results highlighted the model’s ability to eliminate anomalous values and improve prediction consistency. The code will be made publicly available to support future research and development.