Search

Snow detection is imperative in remote sensing for various applications, including climate change monitoring, water resources management, and disaster warning. Recognizing the limitations of current deep learning algorithms in cloud and snow boundary segmentation, as well as issues like detail snow information loss and mountainous snow omission, this paper presents a novel snow detection network based on Swin-Transformer and U-shaped dual-branch encoder structure with geographic information (SD-GeoSTUNet), aiming to address the above issues. Initially, the SD-GeoSTUNet incorporates the CNN branch and Swin-Transformer branch to extract features in parallel and the Feature Aggregation Module (FAM) is designed to facilitate the detail feature aggregation via two branches. Simultaneously, an Edge-enhanced Convolution (EeConv) is introduced to promote snow boundary contour extraction in the CNN branch. In particular, auxiliary geographic information, including altitude, longitude, latitude, slope, and aspect, is encoded in the Swin-Transformer branch to enhance snow detection in mountainous regions. Experiments conducted on Levir_CS, a large-scale cloud and snow dataset originating from Gaofen-1, demonstrate that SD-GeoSTUNet achieves optimal performance with the values of 78.08%, 85.07%, and 92.89% for I o U _ s , F 1 _ s , and M P A , respectively, leading to superior cloud and snow boundary segmentation and thin cloud and snow detection. Further, ablation experiments reveal that integrating slope and aspect information effectively alleviates the omission of snow detection in mountainous areas and significantly exhibits the best vision under complex terrain. The proposed model can be used for remote sensing data with geographic information to achieve more accurate snow extraction, which is conducive to promoting the research of hydrology and agriculture with different geospatial characteristics. [ABSTRACT FROM AUTHOR]

Before 2008, China lacked high-coverage regional surface observation data, making it difficult for the China Meteorological Administration Land Data Assimilation System (CLDAS) to directly backtrack high-resolution, high-quality land assimilation products. To address this issue, this paper proposes a deep learning model named UNET_DCA, based on the UNET architecture, which incorporates a Dual Cross-Attention module (DCA) for multiscale feature fusion by introducing Channel Cross-Attention (CCA) and Spatial Cross-Attention (SCA) mechanisms. This model focuses on the near-surface 10-m wind field and achieves spatial downscaling from 6.25 km to 1 km. We conducted training and validation using data from 2020–2021, tested with data from 2019, and performed ablation experiments to validate the effectiveness of each module. We compared the results with traditional bilinear interpolation methods and the SNCA-CLDASSD model. The experimental results show that the UNET-based model outperforms SNCA-CLDASSD, indicating that the UNET-based model captures richer information in wind field downscaling compared to SNCA-CLDASSD, which relies on sequentially stacked CNN convolution modules. UNET_CCA and UNET_SCA, incorporating cross-attention mechanisms, outperform UNET without attention mechanisms. Furthermore, UNET_DCA, incorporating both Channel Cross-Attention and Spatial Cross-Attention mechanisms, outperforms UNET_CCA and UNET_SCA, which only incorporate one attention mechanism. UNET_DCA performs best on the RMSE, MAE, and COR metrics (0.40 m/s, 0.28 m/s, 0.93), while UNET_DCA_ars, incorporating more auxiliary information, performs best on the PSNR and SSIM metrics (29.006, 0.880). Evaluation across different methods indicates that the optimal model performs best in valleys, followed by mountains, and worst in plains; it performs worse during the day and better at night; and as wind speed levels increase, accuracy decreases. Overall, among various downscaling methods, UNET_DCA and UNET_DCA_ars effectively reconstruct the spatial details of wind fields, providing a deeper exploration for the inversion of high-resolution historical meteorological grid data. [ABSTRACT FROM AUTHOR]

Deep learning methods can achieve a finer refinement required for downscaling meteorological elements, but their performance in terms of bias still lags behind physical methods. This paper proposes a statistical downscaling network based on Light-CLDASSD that utilizes a Shuffle–nonlinear-activation-free block (SNBlock) and Swin cross-attention mechanism (SCAM), and is named SNCA-CLDASSD, for the China Meteorological Administration Land Data Assimilation System (CLDAS). This method aims to achieve a more accurate spatial downscaling of a temperature product from 0.05° to 0.01° for the CLDAS. To better utilize the digital elevation model (DEM) for reconstructing the spatial texture of the temperature field, a module named SCAM is introduced, which can activate more input pixels and enable the network to correct and merge the extracted feature maps with DEM information. We chose 90% of the CLDAS temperature data with DEM and station observation data from 2016 to 2020 (excluding 2018) as the training set, 10% as the verification set, and chose the data in 2018 as the test set. We validated the effectiveness of each module through comparative experiments and obtained the best-performing model. Then, we compared it with traditional interpolation methods and state-of-the-art deep learning super-resolution algorithms. We evaluated the experimental results with HRCLDAS, national stations, and regional stations, and the results show that our improved model performs optimally compared to other methods (RMSE of 0.71 °C/0.12 °C/0.72 °C, BIAS of −0.02 °C/0.02 °C/0.002 °C), with the most noticeable improvement in mountainous regions, followed by plains. SNCA-CLDASSDexhibits the most stable performance in intraday hourly bias at temperature under the conditions of improved feature extraction capability in the SNBlock and a better utilization of the DEM by the SCAM. Due to the replacement of the upsampling method from sub pixels to CARAFE, it effectively suppresses the checkerboard effect and shows better robustness than other models. Our approach extends the downscaling model for CLDAS data products and significantly improves performance in this task by enhancing the model's feature extraction and fusion capabilities and improving upsampling methods. It offers a more profound exploration of historical high-resolution temperature estimation and can be migrated to the downscaling of other meteorological elements. [ABSTRACT FROM AUTHOR]

Due to the low spatial and temporal density of early meteorological observations in China, The China Meteorological Administration Land Data Assimilation System V3.0 (CLDAS3.0) could not obtain high-quality historical, high-resolution assimilated data. In particular, with high-resolution precipitation assimilation data, it is difficult to estimate the precipitation range accurately because of its substantial spatiotemporal heterogeneity. To solve this problem, our team proposes a two-stage downscaling framework for the precipitation field based on multi-task learning, CLDASSD-PRCP. It improves the accuracy of the downscaling task by predicting the precipitation classification mask first. We verify the algorithm using CLDAS3.0 and site observations as ground truth in Yunnan, China. The results show that CLDASSD-PRCP can accurately generate three types of precipitation masks and reduce the MAE of downscaling results by 0.32 mm/h after adding multi-classification masks (MutiClassesMask). In addition, the effects of light and extreme precipitation on precipitation spatial downscaling are also revealed. CLDASSD-PRCP is significant for establishing statistical downscaling models based on deep learning and provides a new way to deal with atmospheric elements with significant spatiotemporal heterogeneity. [Display omitted] • A two-stage precipitation downscaling framework CLDASSD-PRCP based on multi-task learning is proposed • The different effects of precipitation level on the downscaling task are revealed. • The feasibility of CLDASSD-PRCP in CLDAS-V3.0 historical precipitation data back-calculation is verified. [ABSTRACT FROM AUTHOR]

In this article, we developed a hybrid method to estimate surface shortwave radiation (SSR) for the new-generation Himawari-8 geostationary satellite. This hybrid method combines the advantages of a deep neural network (DNN) with high speed and radiative transfer model (RTM) to achieve high accuracy: the RTM provides training data for the DNN under various cloud and aerosol conditions (including heavy aerosol loadings). Moreover, our hybrid method can simultaneously output the byproducts of photosynthetically active radiation (PAR), ultraviolet A (UVA), and Ultraviolet B (UVB), the direct and diffuse components at the surface, and the upward solar radiation at the top-of-atmosphere (TOA). The trained DNN was applied to the Himawari-8 satellite atmospheric products for 2016 and comprehensively validated using a total of 118 stations from four networks located in the full-disk regions of Himawari-8. The results showed an RMSE of 125.9 Wm−2 for instantaneous SSR, 105.4 Wm−2 for hourly SSR, 31.9 Wm−2 for daily SSR, and respective mean bias error (MBE) scores of 8.1, 27.6, and 12.3 Wm−2. The hybrid method developed in this study performed well, achieving high accuracy and high speed, and it is capable of providing near-real-time SSR estimates for many applied energy fields. [ABSTRACT FROM AUTHOR]

• Satellite LAI scheme can provide more accurate vegetation dynamic information. • Satellite LAI scheme improved LST simulation in Noah-MP land surface model. • Mechanism of LAI on LST simulation was revealed by energy budget analysis in model. Leaf area index (LAI) is essential for modelling the land surface temperature (LST) and related energy budget in the land surface models (LSMs). Due to the lack of a parameterization scheme based on satellite LAI data, it is unclear whether satellite LAI data can improve the performance of Noah with multi-parameterization (Noah-MP) LSM to model LST in China land data assimilation system (CLDAS). Here, by using satellite LAI data reconstructed by the advanced deep learning method, we established a new vegetation scheme based on satellite data for the Noah-MP LSM in the CLDAS. We quantitatively evaluated simulation effects of different vegetation schemes including the parameter table scheme (TAB), the dynamic vegetation scheme (DVEG), and the satellite LAI data scheme (OBS), on modelling LAI, LST and their related energy budget in China from 2016 to 2018. We found that except for the cropland, the LAI of the vegetation in growing season observed by satellite was lower than that simulated by the Noah-MP LSM. Validations based on the automatic weather stations in the vegetation-covered area showed that compared with the TAB and DVEG scheme, the OBS scheme improved the negative bias and high unbiased root mean square error (ubRMSE) of simulated LST. Compared with the TAB and DVEG scheme, the optimal improvements of the OBS scheme for annual mean bias and annual mean ubRMSE were 0.32 °C and 0.17 °C, respectively. We further revealed the mechanism of LAI on LST simulation in the Noah-MP LSM by decomposed temperature metric method. With the adoption of the new satellite LAI-based scheme, the absorbed radiation (SW), sensible heat flux (H), latent heat flux (LE), and ground heat flux (G) simulated by the Noah-MP LSM tend to change in different directions, leading to an overall increase in the net energy absorbed by the surface, which is consistent with the LST changes. The LAI changes of dense vegetation affect the LST simulation mainly through the competition of the absorbed shortwave radiation and turbulent heat fluxes. Due to the influence of exposed soil, the LAI changes of sparse vegetation mainly affect the LST simulation mainly through the interaction of the absorbed shortwave radiation and ground heat flux. Our study highlighted that the application of satellite LAI data has the potential to improve simulations of multiple land surface processes in the Noah-MP LSM. [ABSTRACT FROM AUTHOR]