{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:13:36Z","timestamp":1792790016157,"version":"4.5.0"},"reference-count":45,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hainan Provincial Natural Science Foundation of China","award":["623RC455, 623RC457, 425QN244, 626QN0555"],"award-info":[{"award-number":["623RC455, 623RC457, 425QN244, 626QN0555"]}]},{"name":"Scientific Research Fund of Hainan University","award":["KYQD (ZR)-22096, KYQD(ZR)-22097"],"award-info":[{"award-number":["KYQD (ZR)-22096, KYQD(ZR)-22097"]}],"id":[{"id":"https:\/\/ror.org\/03q648j11","id-type":"ROR","asserted-by":"crossref"}]},{"award":["KYQD (ZR)-22096, KYQD(ZR)-22097"],"award-info":[{"award-number":["KYQD (ZR)-22096, KYQD(ZR)-22097"]}],"id":[{"id":"https:\/\/ror.org\/03q648j11","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Lanzhou University\u2013Hainan University Technical Service Project","award":["HD-KYH-2024424"],"award-info":[{"award-number":["HD-KYH-2024424"]}],"id":[{"id":"https:\/\/ror.org\/03q648j11","id-type":"ROR","asserted-by":"crossref"}]},{"award":["HD-KYH-2024424"],"award-info":[{"award-number":["HD-KYH-2024424"]}],"id":[{"id":"https:\/\/ror.org\/03q648j11","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Hainan Provincial Education and Teaching Reform Research Project for Institutions of Higher Learning","award":["Hnjg2026ZC-15"],"award-info":[{"award-number":["Hnjg2026ZC-15"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate wind speed forecasting (WSF) is pivotal for the secure grid integration of wind farms and the optimization of power dispatching. However, the stochastic nature of atmospheric dynamics and their complex interactions with local terrain pose significant challenges. Traditional spatiotemporal models inherently suffer from severe homogenization, irreversibly destroying fine-grained aerodynamic textures and leading to cumulative directional errors over extended horizons. To dismantle these limitations, this study proposes a novel Topography-Guided Spatio-Vertical\u2013Temporal Transformer (TG-SVTFormer) for the multi-step forecasting of zonal and meridional wind vectors. Specifically, a dual-stage topography-guided mechanism explicitly injects static geographical variables (elevation, slope, and roughness) into both the spatial encoding and microscopic decoding phases, imposing key physical constraints on aerodynamic friction. Furthermore, the architecture employs a structured decoupled learning paradigm: a re-engineered Mix-Transformer spatial encoder deliberately eliminates deep-stage downsampling in favor of dilated convolutions\u2014drastically expanding the global receptive field while preserving the intrinsic meteorological textures. Subsequently, the temporal evolution hub explicitly decouples the vertical dimension, utilizing upper-air atmospheric states to guide the target surface layer via simulated vertical momentum transport. The experiments showed the accuracy of TG-SVTFormer in predicting the wind speed with mean absolute error of 0.71 m\/s in 3 h, 0.85 m\/s in 6 h, and 1.06 m\/s in 12 h. Compared to five existing baseline WSF models, the proposed TG-SVTFormer model demonstrates superior performance in wind speed forecasting and, more importantly, offers a transferable and physics-informed framework that can be adapted to other terrain-complex regions and extended to related renewable-energy and air-quality forecasting tasks.<\/jats:p>","DOI":"10.3390\/s26196352","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T16:43:38Z","timestamp":1791564218000},"page":"6352","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Innovative Decoupled Spatio-Vertical\u2013Temporal Learning Model Based on Topography Guidance for Wind Vector Forecasting"],"prefix":"10.3390","volume":"26","author":[{"given":"Xinyu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Cyberspace Security\/School of Cryptology, Hainan University, Renmin Avenue 58, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7683-2589","authenticated-orcid":false,"given":"Huan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security\/School of Cryptology, Hainan University, Renmin Avenue 58, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4685-3645","authenticated-orcid":false,"given":"Xinyue","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security\/School of Cryptology, Hainan University, Renmin Avenue 58, Haikou 570228, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"120890","DOI":"10.1016\/j.techfore.2021.120890","article-title":"Green technology innovation efficiency of energy-intensive industries in China from the perspective of shared resources: Dynamic change and improvement path","volume":"170","author":"Zhu","year":"2021","journal-title":"Technol. Forecast. Soc. Change"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3977","DOI":"10.1016\/j.egyr.2025.11.016","article-title":"A novel point-interval prediction model for wind speed based on hybrid deep learning and RIME optimization algorithms","volume":"14","author":"Huang","year":"2025","journal-title":"Energy Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"7212368","DOI":"10.1155\/2020\/7212368","article-title":"Short-Term Wind Speed Forecasting Based on Ensemble Online Sequential Extreme Learning Machine and Bayesian Optimization","volume":"2020","author":"Quan","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3195","DOI":"10.1038\/s41467-025-58456-4","article-title":"A machine learning model for hub-height short-term wind speed prediction","volume":"16","author":"Zhang","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_5","first-page":"101684","article-title":"A novel dynamic spatio-temporal graph convolutional network with multi-scale transformer for high-resolution wind vector forecasting","volume":"30","author":"Huang","year":"2026","journal-title":"Energy Convers. Manag. X"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100832","DOI":"10.1016\/j.egyai.2026.100832","article-title":"A novel multi-scale spatio-temporal graph attention network for wind vector forecasting","volume":"25","author":"Jian","year":"2026","journal-title":"Energy AI"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1016\/j.renene.2020.09.032","article-title":"Multi-step wind speed prediction by combining a WRF simulation and an error correction strategy","volume":"163","author":"Xu","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.apenergy.2017.04.017","article-title":"Multi-step wind speed and power forecasts based on a WRF simulation and an optimized association method","volume":"197","author":"Zhao","year":"2017","journal-title":"Appl. Energy"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"00034","DOI":"10.1051\/e3sconf\/202233600034","article-title":"Wind Speed Prediction Based on Seasonal ARIMA model","volume":"336","author":"Tyass","year":"2022","journal-title":"E3S Web Conf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0960-1481(98)00001-9","article-title":"A neural networks approach for wind speed prediction","volume":"13","author":"Mohandes","year":"1998","journal-title":"Renew. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.1016\/j.renene.2006.12.001","article-title":"Application of artificial neural networks for the wind speed prediction of target station using reference stations data","volume":"32","author":"Bilgili","year":"2007","journal-title":"Renew. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.renene.2020.11.002","article-title":"A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections","volume":"165","author":"Liu","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_13","unstructured":"Skamarock, W.C., Klemp, J.B., Dudhia, J., Gill, D.O., Liu, Z., Berner, J., Wang, W., Powers, J.G., Duda, M.G., and Barker, D.M. (2019). A Description of the Advanced Research WRF Version 4, National Center for Atmospheric Research. NCAR Technical Note NCAR\/TN-556+STR."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1002\/qj.49711247414","article-title":"Analysis methods for numerical weather prediction","volume":"112","author":"Lorenc","year":"1986","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1016\/j.renene.2018.04.019","article-title":"Improved near surface wind speed predictions using Gaussian process regression combined with numerical weather predictions and observed meteorological data","volume":"126","author":"Hoolohan","year":"2018","journal-title":"Renew. Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.apenergy.2019.01.129","article-title":"Micro-scale wind resource assessment in complex terrain based on CFD coupled measurement from multiple masts","volume":"238","author":"Tang","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"120492","DOI":"10.1016\/j.energy.2021.120492","article-title":"Short-term offshore wind speed forecast by seasonal ARIMA\u2014A comparison against GRU and LSTM","volume":"227","author":"Liu","year":"2021","journal-title":"Energy"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Peng, Y., Qu, X., Shi, J., and Erdem, E. (2021). A Finite Mixture GARCH Approach with EM Algorithm for Energy Forecasting Applications. Energies, 14.","DOI":"10.3390\/en14092352"},{"key":"ref_19","first-page":"100905","article-title":"A modified GM(1, 1) model to accurately predict wind speed","volume":"43","author":"Yousuf","year":"2021","journal-title":"Sustain. Energy Technol. Assess."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.enconman.2017.04.077","article-title":"A combined multivariate model for wind power prediction","volume":"144","author":"Ouyang","year":"2017","journal-title":"Energy Convers. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"119397","DOI":"10.1016\/j.energy.2020.119397","article-title":"Short-term wind speed forecasting using recurrent neural networks with error correction","volume":"217","author":"Duan","year":"2021","journal-title":"Energy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.enconman.2018.11.006","article-title":"Wind speed prediction model using singular spectrum analysis, empirical mode decomposition and convolutional support vector machine","volume":"180","author":"Mi","year":"2019","journal-title":"Energy Convers. Manag."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"104842","DOI":"10.1016\/j.cageo.2021.104842","article-title":"Random-forest based adjusting method for wind forecast of WRF model","volume":"155","author":"Wang","year":"2021","journal-title":"Comput. Geosci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.renene.2019.04.157","article-title":"A novel hybrid system based on multi-objective optimization for wind speed forecasting","volume":"146","author":"Wu","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.egyr.2022.03.092","article-title":"Short-term wind speed prediction based on feature extraction with Multi-task Lasso and Multilayer Perceptron","volume":"8","author":"Wang","year":"2022","journal-title":"Energy Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.enconman.2014.09.060","article-title":"Comparison of new hybrid FEEMD-MLP, FEEMD-ANFIS, Wavelet Packet-MLP and Wavelet Packet-ANFIS for wind speed predictions","volume":"89","author":"Liu","year":"2015","journal-title":"Energy Convers. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27\u201330 June 2016, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_28","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1007\/s10994-019-05815-0","article-title":"Temporal pattern attention for multivariate time series forecasting","volume":"108","author":"Shih","year":"2019","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.enconman.2019.05.007","article-title":"One dimensional convolutional neural network architectures for wind prediction","volume":"195","author":"Harbola","year":"2019","journal-title":"Energy Convers. Manag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"122624","DOI":"10.1016\/j.apenergy.2024.122624","article-title":"Short-term wind speed forecasting using an optimized three-phase convolutional neural network fused with bidirectional long short-term memory network model","volume":"359","author":"Joseph","year":"2024","journal-title":"Appl. Energy"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1175\/MWR-D-24-0248.1","article-title":"Improving sub-seasonal wind-speed forecasts in Europe with a non-linear model","volume":"153","author":"Tian","year":"2025","journal-title":"Mon. Weather Rev."},{"key":"ref_33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is All you Need. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"125231","DOI":"10.1016\/j.energy.2022.125231","article-title":"Multistep short-term wind speed forecasting using transformer","volume":"261","author":"Wu","year":"2022","journal-title":"Energy"},{"key":"ref_35","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_36","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"130404","DOI":"10.1016\/j.energy.2024.130404","article-title":"GAOformer: An adaptive spatiotemporal feature fusion transformer utilizing GAT and optimizable graph matrixes for offshore wind speed prediction","volume":"292","author":"Lin","year":"2024","journal-title":"Energy"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Shikhovtsev, A.Y., Kovadlo, P.G., Lezhenin, A.A., Gradov, V.S., Zaiko, P.O., Khitrykau, M.A., Kirichenko, K.E., Driga, M.B., Kiselev, A.V., and Russkikh, I.V. (2023). Simulating Atmospheric Characteristics and Daytime Astronomical Seeing Using Weather Research and Forecasting Model. Appl. Sci., 13.","DOI":"10.3390\/app13106354"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"136498","DOI":"10.1016\/j.energy.2025.136498","article-title":"LSTM and Transformer-based framework for bias correction of ERA5 hourly wind speeds","volume":"328","author":"Ouarda","year":"2025","journal-title":"Energy"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Shikhovtsev, A.Y., Kovadlo, P.G., and Baron, P. (2025). Candidate Sites for Millimeter and Submillimeter Ground-Based Telescopes: Atmospheric Rating for the Eurasian Submillimeter Telescopes Project. Sensors, 25.","DOI":"10.20944\/preprints202503.1717.v1"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Yang, H.-S., Alkhabbaz, A., and Lee, Y.-H. (2025). Toward Reliable FOWT Modeling: A New Calibration Approach for Extreme Environmental Loads. Energies, 18.","DOI":"10.3390\/en18205545"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kim, I.C., Alkhabbaz, A., Jeong, H., and Lee, Y.H. (2019). Optimization Methodology Of Small Scale Horizontal Axis Shrouded Tidal Current Turbine. Proceedings of the 2019 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), Melbourne, Australia, 9\u201311 December 2019, IEEE.","DOI":"10.1109\/CSDE48274.2019.9162407"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"112897","DOI":"10.1016\/j.rser.2022.112897","article-title":"A transfer method to estimate hub-height wind speed from 10 meters wind speed based on machine learning","volume":"169","author":"Yu","year":"2022","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., and Van Gool, L. (2023). CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 18\u201322 June 2023, IEEE.","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.-H. (2022). Restormer: Efficient Transformer for High-Resolution Image Restoration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18\u201324 June 2022, IEEE.","DOI":"10.1109\/CVPR52688.2022.00564"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6352\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T04:19:09Z","timestamp":1791951549000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":45,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196352"],"URL":"https:\/\/doi.org\/10.3390\/s26196352","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]}}}