{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:52:45Z","timestamp":1781599965675,"version":"3.54.5"},"reference-count":66,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":42,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["rmets.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Meteorological Applications"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate wind prediction is essential for forecasting the transport and decay of wake vortices that might cause an adverse impact to light aircraft operations. This paper proposes an innovative framework for deterministic and probabilistic wind nowcasting, designed to be integrated into a Wake Vortex Warning System for Vertiports (WVWS\u2010V) near major airports. The study presents and tests different deterministic nowcasting models. The superior approach employs a hybrid concept combining complex Continuous Wavelet Transform (CWT), two\u2010dimensional Convolutional Neural Networks (2D\u2010CNN), Long Short\u2010Term Memory (LSTM) networks, and Light Gradient Boosting Machine (LGBM), enabling it to capture both the general patterns and abrupt fluctuations of wind occurring intermittently and repeatedly. The proposed hybrid model achieved a Mean Absolute Error (MAE) of 0.75\u2009m\/s for wind speed and 9.1\u00b0 for wind direction over a 20\u2010min prediction horizon, outperforming all other evaluated models including the statistical persistence prediction method serving as baseline. The probabilistic nowcasting establishing 95% confidence intervals of wind speed and direction utilizes a multivariate\u2010Mixture Density Network (MDN) with weighted Mahalanobis distance. The MDN\u2010based model provides a narrower probability range than the statistical persistence baseline model, with average improvements by 0.91\u2009m\/s for wind speed and 12.05\u00b0 for wind direction. The comparison of the statistical persistence baseline and other machine learning architectures demonstrates that the proposed models achieve superior performance, enabling the WVWS\u2010V to ensure safe and reliable light aircraft operations at vertiports.<\/jats:p>","DOI":"10.1002\/met.70173","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:21:09Z","timestamp":1776039669000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Deep Learning\u2010Based Networks for Deterministic and Probabilistic Wind Nowcasting Within a Wake Vortex Warning System for Vertiport Operations"],"prefix":"10.1002","volume":"33","author":[{"given":"Sooseok","family":"Lee","sequence":"first","affiliation":[{"name":"Institute of Atmospheric Physics, German Aerospace Center (DLR)  Oberpfaffenhofen Germany"},{"name":"Innovation Center for Small Aircraft Technologies (INK) German Aerospace Center (DLR)  W\u00fcrselen Germany"},{"name":"Institute of Flight System Dynamics, RWTH Aachen University  Aachen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"Holz\u00e4pfel","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Physics, German Aerospace Center (DLR)  Oberpfaffenhofen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Stephan","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Physics, German Aerospace Center (DLR)  Oberpfaffenhofen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieter","family":"Moormann","sequence":"additional","affiliation":[{"name":"Institute of Flight System Dynamics, RWTH Aachen University  Aachen Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588\u2010021\u201000183\u2010z"},{"key":"e_1_2_12_3_1","unstructured":"Bahdanau D. K.Cho andY.Bengio.2015.\u201cNeural Machine Translation by Jointly Learning to Align and Translate.\u201din Proceedings of the International Conference on Learning Representations (ICLR).https:\/\/arxiv.org\/abs\/1409.0473."},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107340"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.18280\/ria.330607"},{"key":"e_1_2_12_6_1","volume-title":"Mixture Density Networks","author":"Bishop C. M.","year":"1994"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0202514"},{"key":"e_1_2_12_8_1","first-page":"28","volume-title":"Zwischenbericht: Unfall Cessna 172 r und Robinson r 44 Raven i Bei Aachen\u2010Merzbr\u00fcck (W\u00fcrselen)","author":"Bundesstelle f\u00fcr Flugunfalluntersuchung (BFU)","year":"2022"},{"key":"e_1_2_12_9_1","unstructured":"Cao L. Z.Zhang S.Tang X.Wang andY.Zhang.2017.\u201cSpatial\u2010Temporal Wind Field Prediction by Artificial Neural Networks.\u201dhttps:\/\/arxiv.org\/abs\/1712.05293."},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167\u20102789(90)90035\u2010N"},{"key":"e_1_2_12_11_1","doi-asserted-by":"crossref","unstructured":"Cho K. B.vanMerri\u00ebnboer C.Gulcehre et\u00a0al.2014.\u201cLearning Phrase Representations Using RNN Encoder\u2010Decoder for Statistical Machine Translation.\u201dhttps:\/\/arxiv.org\/abs\/1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"issue":"7","key":"e_1_2_12_12_1","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1002\/cpa.3160410705","article-title":"Orthonormal Bases of Compactly Supported Wavelets","volume":"41","author":"Daubechies I.","year":"1988","journal-title":"Communications on Pure and Applied Mathematics"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:SOLA.0000043578.01201.2d"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.31127\/tuje.1431629"},{"issue":"1","key":"e_1_2_12_15_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum Likelihood From Incomplete Data via the EM Algorithm","volume":"39","author":"Dempster A. P.","year":"1977","journal-title":"Journal of the Royal Statistical Society, Series B: Statistical Methodology"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"e_1_2_12_17_1","unstructured":"EUROCONTROL.2024.\u201cEuropean Wake Turbulence Categorisation and Separation Minima on Approach and Departure (RECAT\u2010EU Edition 2.0).\u201dEUROCONTROL. Edition 2.0.https:\/\/www.eurocontrol.int\/publication\/european\u2010wake\u2010turbulence\u2010categorisation\u2010and\u2010separation\u2010minima\u2010approach\u2010and\u2010departure."},{"key":"e_1_2_12_18_1","first-page":"1","volume-title":"Wavelets in Geophysics","author":"Foufoula\u2010Georgiou E.","year":"1994"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1350482702001020"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.2514\/atcq.17.4.323"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/0515056"},{"issue":"7","key":"e_1_2_12_23_1","first-page":"791","article-title":"MotionUVRNN: A Motion Capture Recurrent Neural Network for Wind Field Forecast Correction via U and V Components Modeling","volume":"51","author":"Gu Z. X.","year":"2024","journal-title":"IAENG International Journal of Computer Science"},{"issue":"1","key":"e_1_2_12_24_1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.2514\/atcq.5.1.3","article-title":"The Development of the Wake Vortices Warning System for Frankfurt Airport: Theory and Implementation","volume":"5","author":"Gurke T.","year":"1997","journal-title":"Air Traffic Control Quarterly"},{"key":"e_1_2_12_25_1","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/BF01456326","article-title":"Zur Theorie Der Orthogonalen Funktionensysteme","volume":"69","author":"Haar A.","year":"1910","journal-title":"Mathematische Annalen"},{"key":"e_1_2_12_26_1","unstructured":"Hinton D. A.2001.\u201cDescription of Selected Algorithms and Implementation Details of a Concept\u2010Demonstration Aircraft Vortex Spacing System (Avoss).\u201dNASA Langley Research Center. Technical Memorandum NASA\/TM\u20102001\u2010211027.https:\/\/ntrs.nasa.gov\/api\/citations\/20010071526\/downloads\/20010071526.pdf."},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.2514\/atcq.17.4.301"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.106618"},{"key":"e_1_2_12_30_1","unstructured":"Ke G. Q.Meng T.Finley et\u00a0al.2017.\u201cLightGBM: A Highly Efficient Gradient Boosting Decision Tree.\u201din Advances in Neural Information Processing Systems. 30.https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/6449f44a102fde848669bdd9eb6b76fa\u2010Paper.pdf."},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/app142411736"},{"key":"e_1_2_12_32_1","doi-asserted-by":"crossref","unstructured":"Kumar V. B. V. M.Nookesh B. S.Saketh S.Syama andJ.Ramprabhakar.2021.\u201cWind Speed Prediction Using Deep Learning\u2010LSTM and GRU.\u201dinProceedings of the 2nd International Conference on Smart Electronics and Communication (ICOSEC 2021)(Bengaluru IEEE). 602\u2013607.","DOI":"10.1109\/ICOSEC51865.2021.9591886"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_12_34_1","doi-asserted-by":"crossref","unstructured":"Liang S. L.Nguyen andF.Jin.2018.\u201cA Multi\u2010Variable Stacked Long\u2010Short Term Memory Network for Wind Speed Forecasting.\u201dhttps:\/\/arxiv.org\/abs\/1811.09735.","DOI":"10.1109\/BigData.2018.8622332"},{"key":"e_1_2_12_35_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2021.103498","article-title":"A Survey on Anomaly Detection for Technical Systems Using LSTM Networks","volume":"131","author":"Lindemann B.","year":"2021","journal-title":"Computers in Industry"},{"key":"e_1_2_12_36_1","doi-asserted-by":"crossref","unstructured":"Liu F. T. K. M.Ting andZ. H.Zhou.2008.\u201cIsolation Forest.\u201dinProceedings of the 2008 Eighth IEEE International Conference on Data Mining (ICDM)413\u2013422.","DOI":"10.1109\/ICDM.2008.17"},{"key":"e_1_2_12_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9061108"},{"key":"e_1_2_12_38_1","first-page":"4898","article-title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","volume":"29","author":"Luo W.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_39_1","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-3-031-04209-6_14","article-title":"Wind Prediction Using Deep Learning and High Performance Computing","volume":"1540","author":"Manero J.","year":"2022","journal-title":"High Performance Computing (CARLA 2021)"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/en14082184"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/9940038"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1190\/1.1441328"},{"key":"e_1_2_12_43_1","unstructured":"National Transportation Safety Board.2022.\u201cAviation Investigation Final Report: Cessna 120 n76646 Upland California.\u201dNational Transportation Safety Board. Accident date: January 3 2022 (12:05 local). Original publish date: June 22 2022. Aviation Investigation Final Report WPR22LA072.https:\/\/data.ntsb.gov\/carol\u2010repgen\/api\/Aviation\/ReportMain\/GenerateNewestReport\/104480\/pdf."},{"key":"e_1_2_12_44_1","unstructured":"O'Hagan A. K.Burke andI. C.Gormley.2015.\u201cInvestigation of Parameter Uncertainty in Clustering Using a Gaussian Mixture Model via Jackknife Bootstrap and Weighted Likelihood Bootstrap.\u201dhttps:\/\/arxiv.org\/abs\/1510.00551."},{"key":"e_1_2_12_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2023397"},{"key":"e_1_2_12_46_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0230026"},{"key":"e_1_2_12_47_1","doi-asserted-by":"crossref","unstructured":"Prabha P. P. V.Vanitha andR.Resmi.2019.\u201cWind Speed Forecasting Using Long Short Term Memory Networks.\u201din Proceedings of the 2019 2nd International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)(IEEE). 1310\u20131314.","DOI":"10.1109\/ICICICT46008.2019.8993279"},{"key":"e_1_2_12_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2022.02.206"},{"key":"e_1_2_12_49_1","volume-title":"Bayesian Non\u2010 and Semi\u2010Parametric Methods and Applications","author":"Rossi P. E.","year":"2014"},{"key":"e_1_2_12_50_1","doi-asserted-by":"crossref","unstructured":"San K. M. J. G.Singh andK. P.Natarajan.2023.\u201cWind Speed Forecasting Using Hybrid Model of CNN and LSTM With Wavelets.\u201din Proceedings of the 2023 International Conference in Advances in Power Signal and Information Technology (APSIT)297\u2013301.","DOI":"10.1109\/APSIT58554.2023.10201713"},{"key":"e_1_2_12_51_1","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23669"},{"key":"e_1_2_12_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_2_12_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1550194"},{"key":"e_1_2_12_54_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/4874757"},{"key":"e_1_2_12_55_1","first-page":"3104","article-title":"Sequence to Sequence Learning With Neural Networks","volume":"27","author":"Sutskever I.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_56_1","unstructured":"Tekin S. F. A.Fazla andS. S.Kozat.2021.\u201cNumerical Weather Forecasting Using Convolutional\u2010LSTM With Attention and Context Matcher Mechanisms.\u201dhttps:\/\/doi.org\/10.48550\/arXiv.2102.00696."},{"key":"e_1_2_12_57_1","doi-asserted-by":"publisher","DOI":"10.5194\/wes\u20107\u20102099\u20102022"},{"key":"e_1_2_12_58_1","doi-asserted-by":"crossref","unstructured":"Thompson E. L. A. G.Taye W.Guo et\u00a0al.2022.\u201cA Survey of eVTOL Aircraft and AAM Operation Hazards.\u201din AIAA Aviation2022 Forum.","DOI":"10.2514\/6.2022-3539"},{"issue":"1","key":"e_1_2_12_59_1","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2","article-title":"A Practical Guide to Wavelet Analysis","volume":"79","author":"Torrence C.","year":"1998","journal-title":"Bulletin of the American Meteorological Society"},{"key":"e_1_2_12_60_1","doi-asserted-by":"crossref","unstructured":"Tran H. T. M. andD.Hogg.2022.\u201cAnomaly Detection Using Prediction Error With Spatio\u2010Temporal Convolutional LSTM.\u201dhttps:\/\/arxiv.org\/abs\/2205.08812.","DOI":"10.31130\/ud-jst.2022.289E"},{"key":"e_1_2_12_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2027628"},{"key":"e_1_2_12_62_1","doi-asserted-by":"publisher","DOI":"10.5194\/wes\u20103\u2010371\u20102018"},{"key":"e_1_2_12_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3135278"},{"key":"e_1_2_12_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3131522"},{"key":"e_1_2_12_65_1","doi-asserted-by":"crossref","unstructured":"Zhang X. Y.Wang Y.Chen X.Cheng andL.Gao.2019.\u201cShort\u2010Term Wind Speed Prediction Based on GRU.\u201din 2019 IEEE Sustainable Power and Energy Conference (iSPEC). 882\u2013887.","DOI":"10.1109\/iSPEC48194.2019.8975256"},{"key":"e_1_2_12_66_1","doi-asserted-by":"crossref","unstructured":"Zhao R. J.Yang D.Song L.Wang J.Liu andY.Xiao.2021.\u201cShort\u2010Term Wind Speed Prediction Based on Data Preprocessing With Discrete Wavelet Transform\u2010Mutual Information and Neural Network.\u201din Proceedings of the IEEE International Conference on Industrial Electronics and Applications (ICIEA)(Changsha China).","DOI":"10.1109\/ICIEA51954.2021.9516271"},{"key":"e_1_2_12_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3105101"}],"container-title":["Meteorological Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/rmets.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/met.70173","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/rmets.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/met.70173","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/rmets.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/met.70173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:06:45Z","timestamp":1781597205000},"score":1,"resource":{"primary":{"URL":"https:\/\/rmets.onlinelibrary.wiley.com\/doi\/10.1002\/met.70173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":66,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1002\/met.70173"],"URL":"https:\/\/doi.org\/10.1002\/met.70173","archive":["Portico"],"relation":{},"ISSN":["1350-4827","1469-8080"],"issn-type":[{"value":"1350-4827","type":"print"},{"value":"1469-8080","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"2025-08-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70173"}}