Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model
Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use dat...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-03 |
|---|---|
| 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 | Leinonen, Jussi Hamann, Ulrich Sideris, Ioannis V Germann, Urs |
| description | Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use data from weather radar, lightning detection, satellite visible/infrared imagery, numerical weather prediction and digital elevation models. We demonstrate the ability of the model to predict lightning, hail and heavy precipitation probabilistically on a 1 km resolution grid, with a temporal resolution of 5 min and lead times up to 60 min. Shapley values quantify the importance of the different data sources, showing that the weather radar products are the most important predictors for all three hazard types. |
| doi_str_mv | 10.48550/arxiv.2211.01001 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2211_01001</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2731612325</sourcerecordid><originalsourceid>FETCH-LOGICAL-a951-465cd8969e2f38f23365f289ecae776d9cabb09a80100f42d3019560b178790f3</originalsourceid><addsrcrecordid>eNotj11LwzAYhYMgOOZ-gFcGvG5N3jRp4p0Mv2Dgze7LuyaxHf0yaZ366-02rw4cDofnIeSGszTTUrJ7DN_1VwrAeco4Y_yCLEAInugM4IqsYtwzxkDlIKVYkM22mjrrQhz70NKuP5QYx7r7oId6rKh1bqCNw9DN1QNF2k7NWCcV_mKw1OKI1E-x7jva9tY11-TSYxPd6j-XZPv8tF2_Jpv3l7f14yZBI3mSKVlabZRx4IX2M5ySHrRxJbo8V9aUuNsxg_qI7zOwgnEjFdvxXOeGebEkt-fbk2oxhLrF8FMclYuT8ry4Oy-G0H9OLo7Fvp9CNzMVkAuuOAiQ4g_FvFiW</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2731612325</pqid></control><display><type>article</type><title>Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Leinonen, Jussi ; Hamann, Ulrich ; Sideris, Ioannis V ; Germann, Urs</creator><creatorcontrib>Leinonen, Jussi ; Hamann, Ulrich ; Sideris, Ioannis V ; Germann, Urs</creatorcontrib><description>Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use data from weather radar, lightning detection, satellite visible/infrared imagery, numerical weather prediction and digital elevation models. We demonstrate the ability of the model to predict lightning, hail and heavy precipitation probabilistically on a 1 km resolution grid, with a temporal resolution of 5 min and lead times up to 60 min. Shapley values quantify the importance of the different data sources, showing that the weather radar products are the most important predictors for all three hazard types.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2211.01001</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Learning ; Data integration ; Data sources ; Deep learning ; Digital Elevation Models ; Digital imaging ; Emergency response ; Infrared imagery ; Lightning detection ; Meteorological radar ; Nowcasting ; Numerical prediction ; Numerical weather forecasting ; Physics - Atmospheric and Oceanic Physics ; Radar detection ; Satellite imagery ; Thunderstorms</subject><ispartof>arXiv.org, 2023-03</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.1029/2022GL101626$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2211.01001$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Leinonen, Jussi</creatorcontrib><creatorcontrib>Hamann, Ulrich</creatorcontrib><creatorcontrib>Sideris, Ioannis V</creatorcontrib><creatorcontrib>Germann, Urs</creatorcontrib><title>Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model</title><title>arXiv.org</title><description>Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use data from weather radar, lightning detection, satellite visible/infrared imagery, numerical weather prediction and digital elevation models. We demonstrate the ability of the model to predict lightning, hail and heavy precipitation probabilistically on a 1 km resolution grid, with a temporal resolution of 5 min and lead times up to 60 min. Shapley values quantify the importance of the different data sources, showing that the weather radar products are the most important predictors for all three hazard types.</description><subject>Computer Science - Learning</subject><subject>Data integration</subject><subject>Data sources</subject><subject>Deep learning</subject><subject>Digital Elevation Models</subject><subject>Digital imaging</subject><subject>Emergency response</subject><subject>Infrared imagery</subject><subject>Lightning detection</subject><subject>Meteorological radar</subject><subject>Nowcasting</subject><subject>Numerical prediction</subject><subject>Numerical weather forecasting</subject><subject>Physics - Atmospheric and Oceanic Physics</subject><subject>Radar detection</subject><subject>Satellite imagery</subject><subject>Thunderstorms</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj11LwzAYhYMgOOZ-gFcGvG5N3jRp4p0Mv2Dgze7LuyaxHf0yaZ366-02rw4cDofnIeSGszTTUrJ7DN_1VwrAeco4Y_yCLEAInugM4IqsYtwzxkDlIKVYkM22mjrrQhz70NKuP5QYx7r7oId6rKh1bqCNw9DN1QNF2k7NWCcV_mKw1OKI1E-x7jva9tY11-TSYxPd6j-XZPv8tF2_Jpv3l7f14yZBI3mSKVlabZRx4IX2M5ySHrRxJbo8V9aUuNsxg_qI7zOwgnEjFdvxXOeGebEkt-fbk2oxhLrF8FMclYuT8ry4Oy-G0H9OLo7Fvp9CNzMVkAuuOAiQ4g_FvFiW</recordid><startdate>20230315</startdate><enddate>20230315</enddate><creator>Leinonen, Jussi</creator><creator>Hamann, Ulrich</creator><creator>Sideris, Ioannis V</creator><creator>Germann, Urs</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>20230315</creationdate><title>Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model</title><author>Leinonen, Jussi ; Hamann, Ulrich ; Sideris, Ioannis V ; Germann, Urs</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a951-465cd8969e2f38f23365f289ecae776d9cabb09a80100f42d3019560b178790f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Data integration</topic><topic>Data sources</topic><topic>Deep learning</topic><topic>Digital Elevation Models</topic><topic>Digital imaging</topic><topic>Emergency response</topic><topic>Infrared imagery</topic><topic>Lightning detection</topic><topic>Meteorological radar</topic><topic>Nowcasting</topic><topic>Numerical prediction</topic><topic>Numerical weather forecasting</topic><topic>Physics - Atmospheric and Oceanic Physics</topic><topic>Radar detection</topic><topic>Satellite imagery</topic><topic>Thunderstorms</topic><toplevel>online_resources</toplevel><creatorcontrib>Leinonen, Jussi</creatorcontrib><creatorcontrib>Hamann, Ulrich</creatorcontrib><creatorcontrib>Sideris, Ioannis V</creatorcontrib><creatorcontrib>Germann, Urs</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</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>Publicly Available Content Database</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>Leinonen, Jussi</au><au>Hamann, Ulrich</au><au>Sideris, Ioannis V</au><au>Germann, Urs</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model</atitle><jtitle>arXiv.org</jtitle><date>2023-03-15</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use data from weather radar, lightning detection, satellite visible/infrared imagery, numerical weather prediction and digital elevation models. We demonstrate the ability of the model to predict lightning, hail and heavy precipitation probabilistically on a 1 km resolution grid, with a temporal resolution of 5 min and lead times up to 60 min. Shapley values quantify the importance of the different data sources, showing that the weather radar products are the most important predictors for all three hazard types.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2211.01001</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2023-03 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2211_01001 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Learning Data integration Data sources Deep learning Digital Elevation Models Digital imaging Emergency response Infrared imagery Lightning detection Meteorological radar Nowcasting Numerical prediction Numerical weather forecasting Physics - Atmospheric and Oceanic Physics Radar detection Satellite imagery Thunderstorms |
| title | Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T06%3A43%3A56IST&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=Thunderstorm%20nowcasting%20with%20deep%20learning:%20a%20multi-hazard%20data%20fusion%20model&rft.jtitle=arXiv.org&rft.au=Leinonen,%20Jussi&rft.date=2023-03-15&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2211.01001&rft_dat=%3Cproquest_arxiv%3E2731612325%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=2731612325&rft_id=info:pmid/&rfr_iscdi=true |