Drought is one of the major global natural disasters, and appropriate monitoring systems are essential to reveal drought trends. In this regard, deep learning is a very promising approach for characterizing the non-linear nature of drought factors. We used multi-source remote sensing data such as the Moderate Resolution Imaging Spectroradiometer (MODIS) and Climate Hazards Group Infrared Precipitation with Station (CHIRPS) data to integrate drought impact factors such as precipitation, vegetation, temperature, and soil moisture. The application of convolutional long short-term memory (ConvLSTM) to construct an integrated drought monitoring model was proposed and tested, using the Xinjiang Uygur Autonomous Region as an example. To better compare the monitoring performance of ConvLSTM models, three other classical deep learning models and three classical machine learning models were also used for comparison. The results show that the composite drought index (CDI) output by the ConvLSTM model had a consistent high correlation with the drought rating of the multi-scale standardized precipitation evapotranspiration index (SPEI). The correlation coefficients between the CDI and the multi-scale standardized precipitation index (SPI) were all above 0.5 (p < 0.01), which was highly significant, and the correlation coefficient between CDI-1 and the monthly soil relative humidity at a 10 cm depth was above 0.45 (p < 0.01), which was well correlated. In addition, the spatial distribution of the CDI-6 simulated by the model was highly correlated with the degree of drought expressed by the SPEI-6 observations at the stations. This study provides a new approach for integrated regional drought monitoring.

Water bodies extraction is important in water resource utilization and flood prevention and mitigation. Remote sensing images contain rich information, but due to the complex spatial background features and noise interference, problems such as inaccurate tributary extraction and inaccurate segmentation occur when extracting water bodies. Recently, using a convolutional neural network (CNN) to extract water bodies is gradually becoming popular. However, the local property of CNN limits the extraction of global information, while Transformer, using a self-attention mechanism, has great potential in modeling global information. This paper proposes the MU-Net, a hybrid MixFormer architecture, as a novel method for automatically extracting water bodies. First, the MixFormer block is embedded into Unet. The combination of CNN and MixFormer is used to model the local spatial detail information and global contextual information of the image to improve the ability of the network to capture semantic features of the water body. Then, the features generated by the encoder are refined by the attention mechanism module to suppress the interference of image background noise and non-water body features, which further improves the accuracy of water body extraction. The experiments show that our method has higher segmentation accuracy and robust performance compared with the mainstream CNN- and Transformer-based semantic segmentation networks. The proposed MU-Net achieves 90.25% and 76.52% IoU on the GID and LoveDA datasets, respectively. The experimental results also validate the potential of MixFormer in water extraction studies.

Near-real-time estimation of precipitation from geostationary satellites plays a vital role in natural disaster mitigation due to timely monitoring, high spatial–temporal resolution, and large coverage, yet this letter remains a large challenge. In this letter, a novel deep learning-based algorithm entitled precipitation estimation using a multiscale network (DLPE-MS) is proposed to estimate precipitation during summer over the eastern Continental United States (CONUS) of America. When inputting bispectral satellite information (10.3 and 6.2 $\mu \text{m}$ ), this algorithm provides near-real-time rainfall rates at hourly and $0.04^{\circ}\times 0.04^{\circ}$ resolution. In order to emphasize the information of a precipitation region at different scales using satellites’ data, we design a multiscale framework based on convolutional neural networks (CNNs). In addition, a loss function named balanced weight mean square error (BWMSE) is proposed to settle the problem of underestimation caused by a shortage in heavy rainy samples. Compared with the mean square error (MSE), the BWMSE has more balance parameters for different objects when training, which is able to mitigate the deviation between the prediction and ground truth in tailed categories (heavy rainy). Results show that this algorithm achieves the highest probability of detection (POD) and correlation coefficient (CC) with the value of 95.5% and 0.5. The statistical results of the precipitation cases also show that the DLPE-MS can significantly improve the estimated values in tailed categories than other products and methods. After testing, this algorithm is able to estimate the precipitation for the study area within 0.19 s.

Precipitation nowcasting is an important tool for economic and social services, especially for forecasting severe weather. The crucial and challenging part of radar echo image prediction is the focus of radar-based precipitation nowcasting. Recently, a number of deep learning models have been designed to solve the problem of extrapolating radar images. Although these methods can generate better results than traditional extrapolation methods, the issue of error accumulation in precipitation forecasting is exacerbated by using only the mean square error (MSE) and mean absolute error (MAE) as loss functions. In this paper, we approach the problem from the perspective of the loss function and propose dynamic weight loss (DWL), a simple but effective loss function for radar echo extrapolation. The method adds model self-adjusted dynamic weights to the weighted loss function and structural similarity index measures. Radar echo extrapolation experiments are performed on four models, ConvLSTM, ConvGRU, PredRNN, and PredRNN++. Radar reflectivity is predicted using Nanjing University C-band Polarimetric (NJU-CPOL) weather radar data. The quantitative statistics show that using the DWL method reduces the MAE of the four models by up to 10.61%, 5.31%, 14.8%, and 13.63%, respectively, over a 1 h prediction period. The results show that the DWL approach is effective in reducing the accumulation of errors over time, improving the predictive performance of currently popular deep learning models.

Snow on the Tibetan Plateau (TP) is not only a freshwater resource for the major rivers in Asia but also plays a significant role in adjusting temperature by reflecting solar radiation. Fractional snow cover mapping with fine spatial and temporal resolution is of great significance for clarifying snow resources and accurately managing snow water resources. However, due to the complex TP topography, the existing FSC retrieval methods are affected by a variety of disturbance factors, resulting in a decrease in accuracy. In this study, a deep learning-based FSC retrieval method, fractional snow cover U-shape net (FSC-USNet), is proposed to improve snow cover mapping accuracy. The input images of FengYun-4A Advanced Geosynchronous Radiation Imager (FY4A/AGRI) and geographic data are extracted using the proposed spatial-channel feature extraction module to characterize the shallow features with texture information into high-dimensional feature images. Additionally, an attention mechanism is introduced to improve the feature differences between different FSC degrees. Finally, the correlation of the decoded features in the channel direction is mined using the channel refinement module to obtain the final FSC results. In this study, a backpropagation artificial neural network (BPANN), random forest, ResNet_FSC, and UNet are trained, compared and validated against the MOA10A1 FSC product. The results show that the proposed method effectively mitigates the problems of unclear texture of snow edges, poor robustness and underestimation in some areas, which exist in other models. Additionally, the proposed method has higher accuracy, with an R2 and explained variance score (EVS) reaching 0.7182 and 0.7332, respectively. Compared to the MOD10A1 snow product, the proposed method exhibits higher detection accuracy in mountainous areas with high snow cover and significantly improves the low snow cover detection rate.

The classification of land use information is important for land resource management. With the purpose of extracting precise spatial information, we present a novel land use classification model based on a mixed attention module and adjustable feature enhancement layer (MAAFEU-net). Our unique design, the mixed attention module, allows the model to concentrate on target-specific discriminative features and capture class-related features within different land use types. In addition, an adjustable feature enhancement layer is proposed to further enhance the classification ability of similar types. We assess the performance of this model using the publicly available GID dataset and the self-built Gwadar dataset. Six semantic segmentation deep networks are used for comparison. The experimental results show that the F1 score of MAAFEU-net is 2.16% and 2.3% higher than the next model and that MIoU is 3.15% and 3.62% higher than the next model. The results of the ablation experiments show that the mixed attention module improves the MIoU by 5.83% and the addition of the adjustable feature enhancement layer can further improve it by 5.58%. Both structures effectively improve the accuracy of the overall land use classification. The validation results show that MAAFEU-net can obtain land use classification images with high precision.