Many deep learning-based spatiotemporal fusion (STF) methods have been proven to achieve high accuracy and robustness. Due to the variable shapes and sizes of objects in remote sensing images, pyramid networks are generally introduced to extract multi-scale features. However, the down-sampling operation in the pyramid structure may lead to the loss of image detail information, affecting the model’s ability to reconstruct fine-grained targets. To address this issue, we propose a novel Dual-Stream Enhanced Pyramid based on Generative Adversarial Network (DSEPGAN) for the spatiotemporal fusion of remote sensing images. The network adopts a dual-stream architecture to separately process coarse and fine images, tailoring feature extraction to their respective characteristics: coarse images provide temporal dynamics, while fine images contain rich spatial details. A reversible feature transformation is embedded in the pyramid feature extraction stage to preserve high-frequency information, and a fusion module employing large-kernel and depthwise separable convolutions captures long-range dependencies across inputs. To further enhance realism and detail fidelity, adversarial training encourages the network to generate sharper and more visually convincing fusion results. The proposed DSEPGAN is compared with widely used and state-of-the-art STF models in three publicly available datasets. The results illustrate that DSEPGAN achieves superior performance across various evaluation metrics, highlighting its notable advantages for predicting seasonal variations in highly heterogeneous regions and abrupt changes in land use.

Landslides are geological hazards that endanger socioeconomic development and ecological security, with landslide susceptibility mapping (LSM) playing a critical role in risk management and spatial planning. Recently, ensemble learning (EL) models have gained attention for effectively addressing the limitations of individual deep learning (DL) models in LSM. However, EL models always built on single-pixel, multi-factor inputs struggle to capture the spatial structure features of terrain units, limiting their ability to depict complex disaster patterns. Moreover, the scarcity of landslide samples and high annotation costs constrain model performance in LSM. To overcome these challenges, we propose a Stacking model based on multidimensional feature collaboration and pseudo-labeling techniques, referred to as MFP_Stacking. A stacking EL model is first employed in MFP_Stacking to integrate global statistical attribute features extracted from one-dimensional vectors with multi-scale spatial topological features derived from three-dimensional vectors. This strategy of multidimensional feature collaborative modeling enhances the model’s ability to learn complex environmental patterns associated with landslides. Subsequently, pseudo-labeling techniques are adopted to incorporate unlabeled data into auxiliary training, thereby addressing the problem of sample scarcity. MFP_Stacking was applied to LSM in the Zigui–Badong section of the Yangtze River Basin and in Ya’an City, Sichuan Province. Experimental results demonstrate that the proposed model performs well in overcoming limitations in feature representation, alleviating sample scarcity, and enhancing the quality of LSM outcomes. It achieved an average improvement of 2.4% for the Zigui–Badong section and 2% for Ya’an City across various evaluation metrics compared to other models.

Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a new fusion detection baseline that uses a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. Based on this approach, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet), which introduces a novel attention-guided self-modulation feature fusion (ASFF) module that adaptively adjusts the responses of fusion features at both global and local levels based on attention information from different modalities, thereby promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that, compared to state-of-the-art methods, our approach achieves a favorable efficiency-accuracy trade-off, reducing the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet.

Soil moisture is a key variable in the global water cycle, carbon balance and energy conversion, and is crucial for hydrological control, meteorological forecasting and crop growth. Pengyang County in Ningxia is a typical region with fragile ecology. In this paper, we utilize Sentinel 1 SAR data and Landsat 8 optical imagery to synergistically invert soil moisture in Pengyang County by combining the advantages of optical and microwave remote sensing. The study calculates the vegetation water content through the VWC model, and uses the water cloud model to eliminate the influence of vegetation on the radar signal to obtain the soil backscattering coefficient with the removal of the influence of vegetation. Finally, the BP neural network model was utilized to invert the soil moisture in Pengyang County. The results show that the VH-polarized SAR data are more sensitive to the vegetation structure and moisture content, which is more suitable for soil moisture inversion in this region, and the NDMI has the highest sensitivity to the vegetation moisture content, which contributes more to the soil moisture estimation. The inversion results of the BP neural network model have a high correlation with the measured values, which indicates that the method can effectively invert the soil moisture in Pangyang County. The results of the study can provide a reference for soil moisture monitoring in the region, and provide a basis for decision-making in ecological protection, water conservation and comprehensive regional management.