Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast
Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-02 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Liu, Zili Hao, Kun Geng, Xiaoyi Shi, Zhenwei |
description | Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is difficult to efficiently extract features from multi-modal data. In this paper, we propose the Dual-Branched spatio-temporal Fusion Network (DBF-Net) -- a novel multi-horizon tropical cyclone track forecasting model which fuses the multi-modal features efficiently. DBF-Net contains a TC features branch that extracts temporal features from 1D inherent features of TCs and a pressure field branch that extracts spatio-temporal features from reanalysis 2D pressure field. Through the encoder-decoder-based architecture and efficient feature fusion, DBF-Net can fully mine the information of the two types of data, and achieve good TCs track prediction results. Extensive experiments on historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant improvement compared with existing statistical and deep learning TCs track forecast methods. |
doi_str_mv | 10.48550/arxiv.2202.13336 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2202_13336</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2634670020</sourcerecordid><originalsourceid>FETCH-LOGICAL-a956-677afea506d65b46fd5cbf330180ccb5308a37d5b456a4a19b26dd0720ca08383</originalsourceid><addsrcrecordid>eNotkMFOwzAMhiMkJKaxB-BEJc4Zbtyk3REGA6QBB3amctNUy9Y1JW2B8fSEjZMl_59-2R9jFzFMk0xKuCb_bT-nQoCYxoioTthIIMY8S4Q4Y5Ou2wCAUKmQEkfs_W6gmt96avTalNFbS711vDe71nmqo8XQWddEL6b_cn4bVc5Hz0PdW7523v6EZOVda3Ug53tdu8aEBelttHDeaOr6c3ZaUd2Zyf8cs9XifjV_5MvXh6f5zZLTTCqu0pQqQxJUqWSRqKqUuqgQIc5A60IiZIRpGSKpKKF4VghVlpAK0AQZZjhml8faw_N56-2O_D7_k5AfJATi6ki03n0MpuvzjRt8E27KhcJEpcEJ4C9dPl-i</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2634670020</pqid></control><display><type>article</type><title>Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast</title><source>Freely Accessible Journals</source><source>arXiv.org</source><creator>Liu, Zili ; Hao, Kun ; Geng, Xiaoyi ; Shi, Zhenwei</creator><creatorcontrib>Liu, Zili ; Hao, Kun ; Geng, Xiaoyi ; Shi, Zhenwei</creatorcontrib><description>Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is difficult to efficiently extract features from multi-modal data. In this paper, we propose the Dual-Branched spatio-temporal Fusion Network (DBF-Net) -- a novel multi-horizon tropical cyclone track forecasting model which fuses the multi-modal features efficiently. DBF-Net contains a TC features branch that extracts temporal features from 1D inherent features of TCs and a pressure field branch that extracts spatio-temporal features from reanalysis 2D pressure field. Through the encoder-decoder-based architecture and efficient feature fusion, DBF-Net can fully mine the information of the two types of data, and achieve good TCs track prediction results. Extensive experiments on historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant improvement compared with existing statistical and deep learning TCs track forecast methods.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2202.13336</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Coders ; Computer Science - Artificial Intelligence ; Computer Science - Learning ; Cyclones ; Encoders-Decoders ; Feature extraction ; Forecasting ; Horizon ; Mathematical models ; Modal data</subject><ispartof>arXiv.org, 2022-02</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,786,887,27932</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2202.13336$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/JSTARS.2022.3170299$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Zili</creatorcontrib><creatorcontrib>Hao, Kun</creatorcontrib><creatorcontrib>Geng, Xiaoyi</creatorcontrib><creatorcontrib>Shi, Zhenwei</creatorcontrib><title>Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast</title><title>arXiv.org</title><description>Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is difficult to efficiently extract features from multi-modal data. In this paper, we propose the Dual-Branched spatio-temporal Fusion Network (DBF-Net) -- a novel multi-horizon tropical cyclone track forecasting model which fuses the multi-modal features efficiently. DBF-Net contains a TC features branch that extracts temporal features from 1D inherent features of TCs and a pressure field branch that extracts spatio-temporal features from reanalysis 2D pressure field. Through the encoder-decoder-based architecture and efficient feature fusion, DBF-Net can fully mine the information of the two types of data, and achieve good TCs track prediction results. Extensive experiments on historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant improvement compared with existing statistical and deep learning TCs track forecast methods.</description><subject>Coders</subject><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Cyclones</subject><subject>Encoders-Decoders</subject><subject>Feature extraction</subject><subject>Forecasting</subject><subject>Horizon</subject><subject>Mathematical models</subject><subject>Modal data</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkMFOwzAMhiMkJKaxB-BEJc4Zbtyk3REGA6QBB3amctNUy9Y1JW2B8fSEjZMl_59-2R9jFzFMk0xKuCb_bT-nQoCYxoioTthIIMY8S4Q4Y5Ou2wCAUKmQEkfs_W6gmt96avTalNFbS711vDe71nmqo8XQWddEL6b_cn4bVc5Hz0PdW7523v6EZOVda3Ug53tdu8aEBelttHDeaOr6c3ZaUd2Zyf8cs9XifjV_5MvXh6f5zZLTTCqu0pQqQxJUqWSRqKqUuqgQIc5A60IiZIRpGSKpKKF4VghVlpAK0AQZZjhml8faw_N56-2O_D7_k5AfJATi6ki03n0MpuvzjRt8E27KhcJEpcEJ4C9dPl-i</recordid><startdate>20220227</startdate><enddate>20220227</enddate><creator>Liu, Zili</creator><creator>Hao, Kun</creator><creator>Geng, Xiaoyi</creator><creator>Shi, Zhenwei</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220227</creationdate><title>Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast</title><author>Liu, Zili ; Hao, Kun ; Geng, Xiaoyi ; Shi, Zhenwei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a956-677afea506d65b46fd5cbf330180ccb5308a37d5b456a4a19b26dd0720ca08383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Coders</topic><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Cyclones</topic><topic>Encoders-Decoders</topic><topic>Feature extraction</topic><topic>Forecasting</topic><topic>Horizon</topic><topic>Mathematical models</topic><topic>Modal data</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Zili</creatorcontrib><creatorcontrib>Hao, Kun</creatorcontrib><creatorcontrib>Geng, Xiaoyi</creatorcontrib><creatorcontrib>Shi, Zhenwei</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Zili</au><au>Hao, Kun</au><au>Geng, Xiaoyi</au><au>Shi, Zhenwei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast</atitle><jtitle>arXiv.org</jtitle><date>2022-02-27</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is difficult to efficiently extract features from multi-modal data. In this paper, we propose the Dual-Branched spatio-temporal Fusion Network (DBF-Net) -- a novel multi-horizon tropical cyclone track forecasting model which fuses the multi-modal features efficiently. DBF-Net contains a TC features branch that extracts temporal features from 1D inherent features of TCs and a pressure field branch that extracts spatio-temporal features from reanalysis 2D pressure field. Through the encoder-decoder-based architecture and efficient feature fusion, DBF-Net can fully mine the information of the two types of data, and achieve good TCs track prediction results. Extensive experiments on historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant improvement compared with existing statistical and deep learning TCs track forecast methods.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2202.13336</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-02 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_2202_13336 |
source | Freely Accessible Journals; arXiv.org |
subjects | Coders Computer Science - Artificial Intelligence Computer Science - Learning Cyclones Encoders-Decoders Feature extraction Forecasting Horizon Mathematical models Modal data |
title | Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T13%3A43%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Dual-Branched%20Spatio-temporal%20Fusion%20Network%20for%20Multi-horizon%20Tropical%20Cyclone%20Track%20Forecast&rft.jtitle=arXiv.org&rft.au=Liu,%20Zili&rft.date=2022-02-27&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2202.13336&rft_dat=%3Cproquest_arxiv%3E2634670020%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2634670020&rft_id=info:pmid/&rfr_iscdi=true |