Cloud detection is a crucial step in the optical satellite image processing pipeline for Earth observation. Clouds in optical remote sensing images seriously affect the visibility of the background and greatly reduce the usability of images for land applications. Traditional methods based on thresholding, multi-temporal or multi-spectral information are often specific to a particular satellite sensor. Convolutional Neural Networks for cloud detection often require labeled cloud masks for training that are very time-consuming and expensive to obtain. To overcome these challenges, this paper presents a hybrid cloud detection method based on the synergistic combination of generative adversarial networks (GAN) and a physics-based cloud distortion model (CDM). The proposed weakly-supervised GAN-CDM method (available online https://github.com/Neooolee/GANCDM) only requires patch-level labels for training, and can produce cloud masks at pixel-level in both training and testing stages. GAN-CDM is trained on a new globally distributed Landsat 8 dataset (WHUL8-CDb, available online doi:https://doi.org/10.5281/zenodo.6420027) including image blocks and corresponding block-level labels. Experimental results show that the proposed GAN-CDM method trained on Landsat 8 image blocks achieves much higher cloud detection accuracy than baseline deep learning-based methods, not only in Landsat 8 images (L8 Biome dataset, 90.20% versus 72.09%) but also in Sentinel-2 images (“S2 Cloud Mask Catalogue” dataset, 92.54% versus 77.00%). This suggests that the proposed method provides accurate cloud detection in Landsat images, has good transferability to Sentinel-2 images, and can quickly be adapted for different optical satellite sensors.

Optical remote sensing has emerged as a crucial technique for earth observation. However, interference of clouds and fog can adversely affect the spatial and spectral information of the images, presenting significant challenges in interpreting remote sensing data and limiting its availability. Moreover, existing methods for addressing the issue of cloud occlusion primarily rely on either physical models or neural networks, lacking a comprehensive integration of the advantages offered by both approaches. So, we propose an end-to-end Asymmetric Unet (AU-Net) dehazing network based on an atmospheric scattering model, which realizes the joint optimization of physical parameters. Firstly, we utilize the Unet to estimate the relatively constant atmospheric light A . Simultaneously, AU-Net based on dark channel prior guidance is used to estimate more complex transmission map T . Next, the atmospheric scattering model is used to deduce the rough dehazing image J based on A and T . Finally, we refine J using AU-Net once again. More specifically, AU-Net incorporates a plug-and-play attention module, namely, Self-Attention with Depth (SAD) and Channel Attention (CA). SAD enhances the fusion of deep semantic information and shallow detail features by expanding the network’s depth, thereby effectively alleviating the dependence of the network on long-distance information. On the other hand, CA addresses the limitations of SAD in terms of channel information. To validate the effectiveness and applicability of proposed dehazing network and attention module, we have achieved state-of-the-art performance and visually appealing results on remote sensing and natural image datasets. The code will be made public on https://github.com/Dudujia160918/Dehazing_Network_AU-Net.

Multi-spectral remote sensing images are widely used for monitoring the globe. Although thin clouds can affect all optical bands, the influences of thin clouds differ with band wavelength. When processing multi-spectral bands at different resolutions, many methods only remove thin clouds in visible/near infrared bands or rescale multi resolution bands to the same resolution then process them together. The former can not make full use of multi-spectral information, and in the latter the rescaling process will introduce noise. In this paper, a deep learning-based thin cloud removal method which fuses full spectral and spatial features in original Sentinel-2 bands is proposed, named CR4S2. A multi input and output architecture is designed for better fusing information in all bands, and reconstructing the background at original resolutions. In addition, two parallel down-sampling residual blocks are designed to transfer features extracted from different depths to the bottom of the network. Experiments were conducted on a new globally distributed Sentinel-2 thin cloud removal dataset called WHUS2-CRv. The results show that the best averaged PSNR, SSIM, nRMSE and SAM of the proposed method over 12 bands in all 20 testing images were 39.55, 0.9443, 0.0245 and 2.5676°, respectively. Compared with baseline methods, the proposed CR4S2 method can better restore not only the spatial features but also spectral features. This indicates that the proposed method is very promising for removing thin clouds in multispectral remote sensing image at different resolutions.

Forest stock volume is the main factor to evaluate forest carbon sink level. At present, the combination of multi-source remote sensing and non-parametric models has been widely used in FSV estimation. However, the biodiversity of natural forests is complex, and the response of the spatial information of remote sensing images to FSV is significantly reduced, which seriously affects the accuracy of FSV estimation. To address this challenge, this paper takes China’s Baishanzu Forest Park with representative characteristics of natural forests as the research object, integrates the forest survey data, SRTM data, and Landsat 8 images of Baishanzu Forest Park, constructs a time series dataset based on survey time, and establishes an FSV estimation model based on the CNN-LSTM-Attention algorithm. The model uses the convolutional neural network to extract the spatial features of remote sensing images, uses the LSTM to capture the time-varying characteristics of FSV, captures the feature variables with a high response to FSV through the attention mechanism, and finally completes the prediction of FSV. The experimental results show that some features (e.g., texture, elevation, etc.) of the dataset based on multi-source data feature variables are more effective in FSV estimation than spectral features. Compared with the existing models such as MLR and RF, the proposed model achieved higher accuracy in the study area (R² = 0.8463, rMSE = 26.73 m³/ha, MAE = 16.47 m³/ha).