To address the challenges of cross-modal feature misalignment and ineffective information fusion caused by the inherent differences in imaging mechanisms, noise statistics, and semantic representations between visible and synthetic aperture radar (SAR) imagery, this paper proposes a multimodal remote sensing object detection method, namely YOLO-CMFM. Built upon the Ultralytics YOLOv11 framework, the proposed approach designs a Cross-Modal Fusion Module (CMFM) that systematically enhances detection accuracy and robustness from the perspectives of modality alignment, feature interaction, and adaptive fusion. Specifically, (1) a Learnable Edge-Guided Attention (LEGA) module is constructed, which leverages a learnable Gaussian saliency prior to achieve edge-oriented cross-modal alignment, effectively mitigating edge-structure mismatches across modalities; (2) a Bidirectional Cross-Attention (BCA) module is developed to enable deep semantic interaction and global contextual aggregation; (3) a Context-Guided Gating (CGG) module is designed to dynamically generate complementary weights based on multimodal source features and global contextual information, thereby achieving adaptive fusion across modalities. Extensive experiments conducted on the OGSOD 1.0 dataset demonstrate that the proposed YOLO-CMFM achieves an $mAP@50$ of 96.2% and an $mAP@50$:95 of 75.1%. While maintaining competitive performance comparable to mainstream approaches at lower IoU thresholds, the proposed method significantly outperforms existing counterparts at high IoU thresholds, highlighting its superior capability in precise object localization. Also, the experimental results on the OSPRC dataset demonstrate that the proposed method can consistently achieve stable gains under different kinds of imaging conditions, including diverse SAR polarizations, spatial resolutions, and cloud occlusion conditions. Moreover, the CMFM can be flexibly integrated into different detection frameworks, which further validates its strong generalization and transferability in multimodal remote sensing object detection tasks.

Satellite time-series data contain information in three dimensions—spatial, spectral, and temporal—and are widely used for monitoring, simulating, and evaluating Earth activities. However, some time-phase images in the satellite time series data are missing due to satellite sensor malfunction or adverse atmospheric conditions, which prevents the effective use of the data. Therefore, we need to complement the satellite time series data with sequence image interpolation. Linear interpolation methods and deep learning methods that have been applied to sequence image interpolation lead to large errors between the interpolation results and the real images due to the lack of accurate estimation of pixel positions and the capture of changes in objects. Inspired by video frame interpolation, we combine optical flow estimation and deep learning and propose a method named Multi-Scale Optical Flow-Intermediate Feature Joint Network. This method learns pixel occlusion and detailed compensation information for each channel and jointly refines optical flow and intermediate features at different scales through an end-to-end network together. In addition, we set a spectral loss function to optimize the network’s learning of the spectral features of satellite images. We have created a time-series dataset using Landsat-8 satellite data and Sentinel-2 satellite data and then conducted experiments on this dataset. Through visual and quantitative evaluation of the experimental results, we discovered that the interpolation results of our method retain better spectral and spatial consistency with the real images, and that the results of our method on the test dataset have a 7.54% lower Root Mean Square Error than other approaches.

Recent advances in satellite missions, particularly the Landsat, Sentinel, and Gaofen series, have led to the rapid accumulation of high-quality remote sensing data with frequent revisits. As these data have become more widely available, Satellite Image Time Series (SITS) have become an important tool for monitoring Earth surface dynamics. SITS now supports a wide range of applications, including precision agriculture, Land Use/Cover Change (LULCC) monitoring, environmental management, and disaster response. This growth has also promoted the development of advanced SITS classification datasets. However, existing reviews have mainly focused on SITS classification algorithms or specific applications, while systematic comparisons of public SITS benchmark datasets remain limited. This lack of synthesis makes it difficult for researchers to navigate fragmented resources and select datasets that match specific scientific or operational tasks. To address this gap, this paper provides a comprehensive review and analysis of 29 publicly available medium-to-high-resolution SITS classification benchmark datasets released between 2017 and 2025. These datasets are intended for training, testing, and validating land-cover classification algorithms, rather than for direct use as operational map products. We conduct a detailed statistical and comparative analysis of these datasets, focusing on their key characteristics across spectral, temporal, and spatial dimensions, as well as their labeling systems. In addition, this review summarizes the SITS classification algorithms that have been developed and benchmarked using these datasets. Finally, we identify the main challenges in constructing and applying SITS classification datasets and discuss future research directions, particularly in data reconstruction, multimodal fusion, change analysis, and advanced model architectures. This survey provides the research community with a systematic overview of SITS classification benchmark datasets and aims to support continued progress in this rapidly developing field.

Land cover dynamics play a critical role in understanding environmental changes, but accurately modeling these dynamics remains a challenge due to the complex interactions between temporal and spatial factors. In this study, we propose a novel temporal–spatial partial differential equation (TS-PDE) modeling method combining sparse regression to uncover the governing equations behind long-term satellite image time series. By integrating temporal and spatial differential terms, the TS-PDE framework captures the intricate interactivity of these factors, overcoming the limitations of traditional pixel-wise prediction methods. Our approach leverages $1\times 1$ convolutional kernels within a convolutional neural network (CNN) solver to approximate derivatives, enabling the discovery of interpretable equations that generalize across temporal–spatial domains. Using MODIS and Planet satellite data, we demonstrate the effectiveness of the TS-PDE method in predicting the value of the normalized difference vegetation index (NDVI) and interpreting the physical significance of the derived equations. The numerical results show that the model achieves good performance, with mean structural similarity index (SSIM) values exceeding 0.82, mean peak signal-to-noise ratio (PSNR) values ranging from 28.5 to 32.8, and mean mean squared error (MSE) values approximating $9\times {10}^{-4}$ for low-resolution MODIS images. For high-resolution Planet images, this study emphasizes the efficacy of TS-PDE in terms of PSNR, SSIM, and MSE metrics, with all datasets exhibiting an average SSIM value of over 0.81, an average PSNR maximum of 30.9, and an average MSE of less than 0.0042. The experimental findings demonstrate the capability of TS-PDE in deriving governing equations and providing effective predictions for the regional-scale dynamics of these time series images. The findings of this study provide potential insights into the mathematical modeling of land cover dynamics.

1. The land surface acts as a critical component of the earth system (Blyth et al. 2021). Land surface processes evolve continuously and strongly affect vegetation growth, water exchange, energy ba...