Shiyao Meng

Accurate cloud detection is a critical preprocessing step in remote sensing applications, as cloud and cloud shadow contamination can significantly degrade the quality of optical satellite imagery. In this paper, we propose CDWMamba, a novel dual-domain neural network that integrates the Mamba-based state space model with discrete wavelet transform (DWT) for effective cloud detection. CDWMamba adopts a four-direction Mamba module to capture long-range dependencies, while the wavelet decomposition enables multi-scale global context modeling in the frequency domain. To further enhance fine-grained spatial features, we incorporate a multi-scale depth-wise separable convolution (MDC) module for spatial detail refinement. Additionally, a spectral–spatial bottleneck (SSN) with channel-wise attention is introduced to promote inter-band information interaction across multi-spectral inputs. We evaluate our method on two benchmark datasets, L8 Biome and S2_CMC, covering diverse land cover types and environmental conditions. Experimental results demonstrate that CDWMamba achieves state-of-the-art performance across multiple metrics, significantly outperforming deep-learning-based baselines in terms of overall accuracy, mIoU, precision, and recall. Moreover, the model exhibits satisfactory performance under challenging conditions such as snow/ice and shrubland surfaces. These results verify the effectiveness of combining a state space model, frequency-domain representation, and spectral–spatial attention for cloud detection in multi-spectral remote sensing imagery.

Long-term investigations of Aerosol Optical Depth (AOD) across Asia are crucial for understanding its regional impacts on the global climate system. However, satellite-derived AOD datasets frequently suffer from missing values due to factors such as cloud cover, algorithmic limitations, and various atmospheric conditions. To overcome these challenges, this study employs the deep learning model TabNet, incorporating Digital Elevation Model (DEM) data and ERA5 meteorological variables, to fuse MERRA-2 AOD with MODIS MAIAC AOD observations. The resulting integration yields a high-resolution, seamless daily AOD dataset for Asia spanning the period from 2001 to 2024. The fused dataset demonstrates significant improvements over the original MERRA-2 AOD, with an increase in the coefficient of determination (R²) by 0.1065 and a reduction in root mean square error (RMSE) by 0.0369. Spatio-temporal analysis, conducted using Empirical Orthogonal Function (EOF) decomposition, reveals that AOD concentrations across Asia are strongly influenced by anthropogenic factors, including industrial activities, transportation emissions, and biomass burning. The results indicate a generally increasing trend in AOD from 2001 to 2014, followed by a declining trend from 2015 to 2024. Notably, EOF results show a marked rise in AOD levels in Mongolia after 2020, likely attributable to an uptick in dust storm activity. This research offers valuable insights into the spatiotemporal trends of aerosols across Asia, underscoring the need for sustained air quality measures to mitigate pollution and protect public health.

Currently, the main remote sensing-based crop mapping methods are based on spectral-temporal features. However, there has been a lack research on the selection of the multi-temporal images, and most of the methods are based on the use of all the available images during the cycle of crop growth. In this study, in order to explore the optimal temporal window for crop mapping with limited remote sensing data, we tested all possible combinations of temporal windows in an exhaustive manner, and made a comprehensive consideration of the spatial accuracy and statistical accuracy as evaluation indices. We collected all the available cloud-free Sentinel-2 multi-spectral images for the winter wheat and rapeseed growth periods in the study area in southern China, and used the random forest (RF) method as the classifier to identify the optimal temporal window. The spatial and statistical accuracies of all the results were assessed by using ground survey data and local agricultural census data. The optimal temporal window for the mapping of winter wheat and rapeseed in the study area was obtained by identifying the best-performing set of results. In addition, the variable importance (VI) index was used to evaluate the importance of the different bands for crop mapping. The results of the spatial accuracy, statistical accuracy, and the VI showed that the combinations of images from the later stages of crop growth were more suitable for crop mapping.