{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Guo D"],"funding":["National Natural Science Foundation of China (National Science Foundation of China)"],"pagination":["633"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12816100"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["17(1)"],"pubmed_abstract":["Flight trajectory prediction is a fundamental task in air traffic control. While our previous WTFTP framework leveraged wavelet-based time-frequency analysis for trajectory prediction, its iterative single-horizon paradigm suffers from error accumulation in long-horizon forecasts. Here, the WTFTP+ framework is proposed to enhance multi-horizon prediction performance while further exploring the potential of time-frequency analysis in flight trajectory prediction tasks. An encoder-decoder neural architecture is designed to generate wavelet components of predicted trajectories, where a direct multi-horizon prediction paradigm is employed to mitigate the cumulative errors of the WTFTP. Additionally, a time-frequency bridging mechanism is proposed to explore intrinsic correlations among multi-s"],"journal":["Nature communications"],"pubmed_title":["Multi-horizon flight trajectory prediction enabled by time-frequency wavelet transform."],"pmcid":["PMC12816100"],"funding_grant_id":["62401380","62371323"],"pubmed_authors":["Liu J","Zhang Z","Zhang J","Guo D","Lin Y"],"additional_accession":[]},"is_claimable":false,"name":"Multi-horizon flight trajectory prediction enabled by time-frequency wavelet transform.","description":"Flight trajectory prediction is a fundamental task in air traffic control. While our previous WTFTP framework leveraged wavelet-based time-frequency analysis for trajectory prediction, its iterative single-horizon paradigm suffers from error accumulation in long-horizon forecasts. Here, the WTFTP+ framework is proposed to enhance multi-horizon prediction performance while further exploring the potential of time-frequency analysis in flight trajectory prediction tasks. An encoder-decoder neural architecture is designed to generate wavelet components of predicted trajectories, where a direct multi-horizon prediction paradigm is employed to mitigate the cumulative errors of the WTFTP. Additionally, a time-frequency bridging mechanism is proposed to explore intrinsic correlations among multi-s","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-16T03:07:46.666Z","creation":"2026-06-16T03:05:51.671Z"},"accession":"S-EPMC12816100","cross_references":{"pubmed":["41381579"],"doi":["10.1038/s41467-025-67399-9"]}}