[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118720-en":3,"doc-seo-118720-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118720,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes","Despite the critical need to quantify how extreme precipitation spatial patterns evolve under warming, existing approaches struggle to analyze storm-scale model outputs in an objective and information-preserving way. This work introduces an unsupervised machine learning framework that quantifies how storm dynamics drive precipitation extremes and their changes without discarding spatial structure. Results across many precipitation quantiles show that changes are dominated by spatial shifts in storm regimes rather than intrinsic changes in regime precipitation production.","arXiv:2211.01613v1 [[physics. ao-ph](physics. ao-ph)] 3 Nov 2022  \nAn Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation  \nChanges  \nGriffin Mooers  \nUniversity of California at Irvine Irvine, CA [gmooers96@gmail.com](gmooers96@gmail.com)  \nMike Pritchard  \nUniversity of California at Irvine Irvine, CA[mspritch@uci.edu](mspritch@uci.edu)  \nTom Beucler  \nUniversity of Lausanne Lausanne, CH [tom.beucler@unil.ch](tom.beucler@unil.ch)  \nStephan Mandt  \nUniversity of California at Irvine Irvine, CA[mandt@uci.edu](mandt@uci.edu)  \nAbstract  \nDespite the importance of quantifying how the spatial patterns of extreme precipitation will change with warming, we lack tools to objectively analyze the storm-scale outputs of modern climate models. To address this gap, we develop an unsupervised machine learning framework to quantify how storm dynamics affect precipitation extremes and their changes without sacrificing spatial information.  \nOver a wide range of precipitation quantiles, we find that the spatial patterns of extreme precipitation changes are dominated by spatial shifts in storm regimes rather than intrinsic changes in how these storm regimes produce precipitation.  \n1 Introduction: Understanding the Changing Spatial Patterns of Precipitation Extremes  \nAccording to the latest IPCC report [9],“ there is high confidence that extreme precipitation events across the globe will increase in both intensity and frequency with global warming”. As the severity of storms and tropical cyclones magnifies, there will be associated increases in flood-related risk [13] and challenges in water management [2, 3] . To first order, heavy precipitation extremes are limited by the water vapor holding capacity of the atmosphere, which increases by about 7% per 1K (Kelvin) of warming following an approximate Clausius-Clapeyron scaling [24] . This is referred to as the“thermodynamic contribution” to extreme precipitation changes [12] and gives a solid theoretical foundation for spatially-averaged changes in precipitation extremes.  \nYet climate change adaptation requires knowledge of how precipitation extremes will change atthe local scale, i.e., understanding the changing spatial patterns of precipitation extremes under warming. Focusing on the tropics, where most of the vulnerable world population lives [11], these changing spatial patterns are primarily dictated by atmospheric vertical velocity (“dynamical”) changes because horizontal spatial gradients in temperatures are weak. This is referred to as the“dynamic contribution” to extreme precipitation changes [12] .  \nA comprehensive understanding of this “dynamic contribution” remains elusive. Approximate scalings can be derived based on quasi-geostrophic dynamics [18, 23] and convective storm dynamics [22, 1] . But actionable findings require Earth-like simulations of the present and future climates (e.g., [25]), which can resolve regional circulation changes and their effects on storms in their full com  \nTackling Climate Change with Machine Learning workshop at NeurIPS 2022 .  \nplexity. These simulations are computationally demanding and output large amounts of multi-scale, three-dimensional data that challenge traditional data analysis tools. For example, the state-of-the-art high-resolution 1 , SPCAM (Super Parameterized Community Atmospheric Model,[15, 16]) simulations we will use in this study (SI-A) output 3.4 Terabytes of data, with 76,944,384 samples of precipitation and the corresponding storm-scale vertical velocity fields (see Fig 1 for examples) .  \nSelected SPCAM Vertical Velocity Fields  \nhPa hPa  \n200  \n400  \n600  \n800  \n200  \n400  \n600  \n800  \n(a) 0K 5th %  \n0.0 mm/day  \n(e) +4K 5th %  \n0.0 mm/day  \n50 100 Columns  \n(b) 0K 50th % (c) 0K 85th % (d) 0K 95th % 0.4 mm/day 8.0 mm/day 22.7 mm/day  \n(f) +4K 50th % (g) +4K 85th % (h) +4K 95th %  \n\n| 0.3 mm/day |  |  8.1 mm/day |  | 27.6 mm/day |  |\n| --- | --- | --- | --- | --- | --- |\n|  |  |  |  |  |  |\n\n2.0  \n","cbCaim7xvk7OI4Jk","https://ap.wps.com/l/cbCaim7xvk7OI4Jk","pdf",2404996,1,14,"English","en",105,"# Abstract\n# Introduction: Understanding the Changing Spatial Patterns of Precipitation Extremes\n## Thermodynamic vs. dynamic contributions to extreme precipitation\n## Data challenges from high-resolution climate simulations\n## Clustering vertical velocity fields into convection regimes\n## Decomposing changes in precipitation extremes","[{\"question\":\"What problem does the paper address about extreme precipitation changes under warming?\",\"answer\":\"It targets the lack of objective tools to analyze storm-scale outputs from modern climate models while preserving spatial information about how extremes change with warming.\"},{\"question\":\"How does the proposed method relate storm dynamics to precipitation extremes?\",\"answer\":\"It clusters storm vertical velocity fields into interpretable convection regimes using unsupervised machine learning, then links changes in precipitation extremes to changes in regime probabilities and dynamics.\"},{\"question\":\"What dominates spatial pattern changes in extreme precipitation across precipitation quantiles?\",\"answer\":\"The spatial patterns of extreme precipitation changes are dominated by spatial shifts in storm regimes rather than by intrinsic changes in how those regimes produce precipitation.\"}]","An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes | PDF",1785719904,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"an-unsupervised-learning-perspective-on-the-dynamic-contribution-to-extreme-precipitation-changes","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/an-unsupervised-learning-perspective-on-the-dynamic-contribution-to-extreme-precipitation-changes/118720/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address about extreme precipitation changes under warming?","Question",{"text":76,"@type":77},"It targets the lack of objective tools to analyze storm-scale outputs from modern climate models while preserving spatial information about how extremes change with warming.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method relate storm dynamics to precipitation extremes?",{"text":81,"@type":77},"It clusters storm vertical velocity fields into interpretable convection regimes using unsupervised machine learning, then links changes in precipitation extremes to changes in regime probabilities and dynamics.",{"name":83,"@type":74,"acceptedAnswer":84},"What dominates spatial pattern changes in extreme precipitation across precipitation quantiles?",{"text":85,"@type":77},"The spatial patterns of extreme precipitation changes are dominated by spatial shifts in storm regimes rather than by intrinsic changes in how those regimes produce precipitation.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]