{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:44:34Z","timestamp":1780526674738,"version":"3.54.1"},"reference-count":39,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002885","name":"National Meteorological Information Center of China Meteorological","doi-asserted-by":"publisher","award":["NMICJY202305"],"award-info":[{"award-number":["NMICJY202305"]}],"id":[{"id":"10.13039\/501100002885","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002885","name":"National Meteorological Information Center of China Meteorological","doi-asserted-by":"publisher","award":["202302035765"],"award-info":[{"award-number":["202302035765"]}],"id":[{"id":"10.13039\/501100002885","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002885","name":"National Meteorological Information Center of China Meteorological","doi-asserted-by":"publisher","award":["91437105"],"award-info":[{"award-number":["91437105"]}],"id":[{"id":"10.13039\/501100002885","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002885","name":"National Meteorological Information Center of China Meteorological","doi-asserted-by":"publisher","award":["92037000"],"award-info":[{"award-number":["92037000"]}],"id":[{"id":"10.13039\/501100002885","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002885","name":"National Meteorological Information Center of China Meteorological","doi-asserted-by":"publisher","award":["42205153"],"award-info":[{"award-number":["42205153"]}],"id":[{"id":"10.13039\/501100002885","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GHFUND C","award":["NMICJY202305"],"award-info":[{"award-number":["NMICJY202305"]}]},{"name":"GHFUND C","award":["202302035765"],"award-info":[{"award-number":["202302035765"]}]},{"name":"GHFUND C","award":["91437105"],"award-info":[{"award-number":["91437105"]}]},{"name":"GHFUND C","award":["92037000"],"award-info":[{"award-number":["92037000"]}]},{"name":"GHFUND C","award":["42205153"],"award-info":[{"award-number":["42205153"]}]},{"name":"National Nature Science Foundation of China","award":["NMICJY202305"],"award-info":[{"award-number":["NMICJY202305"]}]},{"name":"National Nature Science Foundation of China","award":["202302035765"],"award-info":[{"award-number":["202302035765"]}]},{"name":"National Nature Science Foundation of China","award":["91437105"],"award-info":[{"award-number":["91437105"]}]},{"name":"National Nature Science Foundation of China","award":["92037000"],"award-info":[{"award-number":["92037000"]}]},{"name":"National Nature Science Foundation of China","award":["42205153"],"award-info":[{"award-number":["42205153"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>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\u20132021, 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.<\/jats:p>","DOI":"10.3390\/rs16111867","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T11:37:13Z","timestamp":1716464233000},"page":"1867","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Enhanced Wind Field Spatial Downscaling Method Using UNET Architecture and Dual Cross-Attention Mechanism"],"prefix":"10.3390","volume":"16","author":[{"given":"Jieli","family":"Liu","sequence":"first","affiliation":[{"name":"Datong Meteorological Bureau, Datong 037010, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunxiang","family":"Shi","sequence":"additional","affiliation":[{"name":"National Meteorological Information Center, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-2264","authenticated-orcid":false,"given":"Lingling","family":"Ge","sequence":"additional","affiliation":[{"name":"National Meteorological Information Center, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruian","family":"Tie","sequence":"additional","affiliation":[{"name":"National Meteorological Information Center, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojian","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanxi Meteorological Information Center, Taiyuan 030006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Yuncheng Meteorological Bureau, Yuncheng 044000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Independent Researcher, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanfei","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1007\/s13351-019-9042-9","article-title":"Development and evaluation of hourly and kilometer resolution retrospective and real-time surface meteorological blended forcing dataset (SMBFD) in China","volume":"33","author":"Han","year":"2019","journal-title":"J. Meteorol. Res."},{"key":"ref_2","first-page":"267","article-title":"Climate change 2001: The scientific basis","volume":"Volume 57","author":"Griggs","year":"2002","journal-title":"Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1002\/2015MS000559","article-title":"An evaluation of the variable-resolution CESM for modeling California\u2019s climate","volume":"8","author":"Huang","year":"2016","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1007\/s00382-015-2619-9","article-title":"Simulation of seasonal US precipitation and temperature by the nested CWRF-ECHAM system","volume":"46","author":"Chen","year":"2016","journal-title":"Clim. Dyn."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/S0022-1694(01)00529-7","article-title":"Multivariate stochastic downscaling model for generating daily precipitation series based on atmospheric circulation","volume":"256","year":"2002","journal-title":"J. Hydrol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1002\/joc.1597","article-title":"Assessments of Mediterranean precipitation changes for the 21st century using statistical downscaling techniques","volume":"28","author":"Hertig","year":"2008","journal-title":"Int. J. Climatol. J. R. Meteorol. Soc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"203","DOI":"10.3354\/cr00731","article-title":"Simulation of extreme weather events by a stochastic weather generator","volume":"35","author":"Semenov","year":"2008","journal-title":"Clim. Res."},{"key":"ref_8","first-page":"101","article-title":"Stochastic weather generators: An overview of weather type models","volume":"156","author":"Ailliot","year":"2015","journal-title":"J. Soci\u00e9t\u00e9 Fran\u00e7aise Stat."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1016\/j.jhydrol.2017.12.015","article-title":"A spatial downscaling of soil moisture from rainfall, temperature, and AMSR2 using a Gaussian-mixture nonstationary hidden Markov model","volume":"564","author":"Kwon","year":"2018","journal-title":"J. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sun, X., Wang, J., Zhang, L., Ji, C., Zhang, W., and Li, W. (2022). Spatial downscaling model combined with the Geographically Weighted Regression and multifractal models for monthly GPM\/IMERG precipitation in Hubei Province, China. Atmosphere, 13.","DOI":"10.3390\/atmos13030476"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., and Loy, C.C. (2022, January 18\u201324). Basicvsr++: Improving video super-resolution with enhanced propagation and alignment. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ranade, R., Liang, Y., Wang, S., Bai, D., and Lee, J. (2022, January 7\u201313). 3D Texture Super Resolution via the Rendering Loss. Proceedings of the ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Virtual.","DOI":"10.1109\/ICASSP43922.2022.9747751"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104110","DOI":"10.1016\/j.earscirev.2022.104110","article-title":"A comprehensive review on deep learning based remote sensing image super-resolution methods","volume":"232","author":"Wang","year":"2022","journal-title":"Earth-Sci. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Choi, H., Lee, J., and Yang, J. (2023, January 17\u201324). N-gram in swin transformers for efficient lightweight image super-resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00206"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7211","DOI":"10.1109\/TGRS.2020.3032790","article-title":"Stochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network","volume":"59","author":"Leinonen","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e2020WR029308","DOI":"10.1029\/2020WR029308","article-title":"Deep learning for daily precipitation and temperature downscaling","volume":"57","author":"Wang","year":"2021","journal-title":"Water Resour. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e2022MS003120","DOI":"10.1029\/2022MS003120","article-title":"A generative deep learning approach to stochastic downscaling of precipitation forecasts","volume":"14","author":"Harris","year":"2022","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Gerges, F., Boufadel, M.C., Bou-Zeid, E., Nassif, H., and Wang, J.T.L. (2022, January 15\u201317). A Novel Deep Learning Approach to the Statistical Downscaling of Temperatures for Monitoring Climate Change. Proceedings of the 2022 The 6th International Conference on Machine Learning and Soft Computing, Haikou, China.","DOI":"10.1145\/3523150.3523151"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., and Ganguly, A.R. (2017, January 13\u201317). Deepsd: Generating high resolution climate change projections through single image super-resolution. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.","DOI":"10.1145\/3097983.3098004"},{"key":"ref_20","unstructured":"Mao, Z. (2019). Spatial Downscaling of Meteorological Data Based on Deep Learning Image Super-Resolution. [Master\u2019s Thesis, Wuhan University]."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/s00376-021-0438-y","article-title":"CLDASSD: Reconstructing fine textures of the temperature field using super-resolution technology","volume":"39","author":"Tie","year":"2022","journal-title":"Adv. Atmos. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1175\/JTECH-D-21-0099.1","article-title":"To Accurately and Lightly Downscale the Temperature Field by Deep Learning","volume":"39","author":"Tie","year":"2022","journal-title":"Ournal Atmos. Ocean. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shen, Z., Shi, C., Shen, R., Tie, R., and Ge, L. (2023). Spatial Downscaling of Near-Surface Air Temperature Based on Deep Learning Cross-Attention Mechanism. Remote Sens., 15.","DOI":"10.3390\/rs15215084"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e1961","DOI":"10.1002\/met.1961","article-title":"A comparative study of convolutional neural network models for wind field downscaling","volume":"27","author":"Kern","year":"2020","journal-title":"Meteorol. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"553","DOI":"10.5194\/npg-30-553-2023","article-title":"Downscaling of surface wind forecasts using convolutional neural networks","volume":"30","author":"Dupuy","year":"2023","journal-title":"Nonlinear Process. Geophys."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1038\/s41597-023-02805-9","article-title":"Deep learning downscaled high-resolution daily near surface meteorological datasets over east asia","volume":"10","author":"Lin","year":"2023","journal-title":"Sci. Data"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107139","DOI":"10.1016\/j.engappai.2023.107139","article-title":"Dual Cross-Attention for medical image segmentation","volume":"126","author":"Gorkem","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Huo, C., Zhu, J., Huo, L., and Pan, C. (2023). DCAT: Dual Cross-Attention-Based Transformer for Change Detection. Comput. Biol. Med., 15.","DOI":"10.3390\/rs15092395"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Fu, Z., Li, J., and Hua, Z. (2022). DEAU-Net: Attention networks based on dual encoder for Medical Image Segmentation. Comput. Biol. Med., 150.","DOI":"10.1016\/j.compbiomed.2022.106197"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Han, S., Liu, B., Shi, C., Liu, Y., Qiu, M., and Sun, S. (2020). Evaluation of CLDAS and GLDAS datasets for Near-surface Air Temperature over major land areas of China. Sustainability, 12.","DOI":"10.3390\/su12104311"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1080\/13658810601169899","article-title":"An evaluation of void-filling interpolation methods for SRTM data","volume":"21","author":"Reuter","year":"2007","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_32","unstructured":"(2020). Meteorological Observation Data Quality Control (Standard No. QX\/T 118-2020)."},{"key":"ref_33","unstructured":"Olaf, R., Philipp, F., and Thomas, B. (2015, January 5\u20139). U-net: Convolutional networks for biomedical images egmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., and Johansen, H.D. (2020, January 28\u201330). Doubleu-net: A deep convolutional neural network for medical image segmen-tation. Proceedings of the 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), Rochester, MN, USA.","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/s42774-023-00148-y","article-title":"Deep learning method for super-resolution reconstruction of the spatio-temporal flow field","volume":"5","author":"Bao","year":"2023","journal-title":"Adv. Aerodyn."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Zhang, J., Chen, W., Wang, Y., You, J., and Wang, Q. (2022). SR-DeblurUGAN: An End-to-End Super-Resolution and Deblurring Model with High Performance. Drones, 6.","DOI":"10.3390\/drones6070162"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.neucom.2021.08.137","article-title":"SGUNet: Style-guided UNet for adversely conditioned fundus image super-resolution","volume":"465","author":"Fan","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mela, C.A., and Liu, Y. (2021). Application of convolutional neural networks towards nuclei segmentation in localization-based super-resolution fluorescence microscopy images. BMC Bioinform., 1.","DOI":"10.1186\/s12859-021-04245-x"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1175\/JAM2463.1","article-title":"Description and evaluation of the characteristics of the NCAR high-resolution land data assimilation system","volume":"46","author":"Chen","year":"2007","journal-title":"J. Appl. Meteorol. Climatol."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/11\/1867\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:47:35Z","timestamp":1760107655000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/11\/1867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["rs16111867"],"URL":"https:\/\/doi.org\/10.3390\/rs16111867","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,23]]}}}