[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118416-en":3,"doc-seo-118416-105":30,"detail-sidebar-cat-0-en-105":83},{"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":4,"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},118416,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Characterizing uncertainty in deep convection triggering using explainable machine learning","Realistically representing deep atmospheric convection is essential for accurate numerical weather and climate simulations, yet the triggering of where and when convection occurs remains a major source of model uncertainty. Most convective triggers are deterministic and ignore uncertainty in the evolving convective state. This study builds a random-forest machine learning model to predict the probability of deep convection, then applies SHAP value clustering to quantify uncertainty in convective events and identify driving mechanisms. The approach uses ARM constrained variational analysis observations and shows probabilistic triggers can outperform conventional schemes.","LaTeX File ( .tex, .sty, .cls, . bst, . bib)   \nGenerated using the official AMS LATEX template v6.1  \nCharacterizing uncertainty in deep convection triggering using explainable machine learning  \nGreta A. Millera Philip Stier,a Hannah M. Christensen,a  \na Department of Physics, University of Oxford, Oxford, UK  \nCorresponding author: Greta A. Miller, [greta.miller@physics.ox.ac.uk](greta.miller@physics.ox.ac.uk)  \n1  \nEarly Online Release: This preliminary version has been accepted for publication in Journal of the Atmospheric Sciences, may be fully cited, and has been assigned DOI 10. 1175/JAS-D-24-0085 .1. The final typeset copyedited article will replace the EOR at the above DOI when it is published.  \n© 2025 The Author(s) . Published by the American Meteorological Society. This is an Author Accepted Manuscript distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4 .0)  \nLicense  .  \nBrought to you by UNIVERSITY OF OXFORD-RADCLIFFE | Unauthenticated | Downloaded 04/29/25 09:13 AM UTC  \nABSTRACT: Realistically representing deep atmospheric convection is important for accurate numerical weather and climate simulations. However, parameterizing where and when deep convection occurs (“triggering”) is a well-known source of model uncertainty. Most triggers parameterize convection deterministically, without considering the uncertainty in the convective state as a stochastic process. In this study, we develop a machine learning model, a random forest, that predicts the probability of deep convection, and then apply clustering of SHAP values, an explainable machine learning method, to characterize the uncertainty of convective events. The model uses observed large-scale atmospheric variables from the Atmospheric Radiation Measurement constrained variational analysis dataset over the Southern Great Plains, US. The analysis of feature importance shows which mechanisms driving convection are most important, with largescale vertical velocity providing the highest predictive power for more certain, or easier to predict, convective events, followed by the dynamic generation rate of dilute convective available potential energy. Predictions of uncertain, or harder to predict, convective events instead rely more on other features such as precipitable water or low-level temperature. The model outperforms conventional convective triggers. This suggests that probabilistic machine learning models can be used as stochastic parameterizations to improve the occurrence of convection in weather and climate models in the future.  \n2  \nAccepted for publication in JournBaogfhttthoobNoIVsEpSIeTrYicOOcFORDence-RsADCIFIF0| UatetaAtedS| D- w-n2lod-e0d0/2/215.09:13 AM UTC  \nSIGNIFICANCE STATEMENT: Convective storms, which produce clouds and precipitation, are difficult to represent in models since they occur at scales smaller than a model grid box. The purpose of this study is to better understand why convection is sometimes easier or harder to predict with certainty. This is important because predicting where and when convection occurs in atmospheric models affects the energy, moisture, and momentum processes in these models, which is known to lead to errors in weather forecasts and climate projections. This work highlights the importance of representing uncertainty in processes like convection.  \n1. Introduction  \nAtmospheric convection plays a crucial role in Earth’s climate system. By transporting mass and energy from the surface to the tropopause, convection impacts the global water, energy, and momentum budgets (Plant and Yano 2015) . Convection also produces clouds that affect the radiation budget (Jones et al. 2023; Hartmann 2016) . Severe weather events linked to atmospheric convection can result in substantial socioeconomic impacts such as loss of lives and property. It is therefore essential to represent convection accurately in atmospheric simulations.  \nTo explicitly resolve individual convective cells and th","cbCaiiu683Isc0Pu","https://ap.wps.com/l/cbCaiiu683Isc0Pu","pdf",9399400,1,39,"English","en",105,"# Abstract\n# Significance Statement\n# Introduction","[{\"question\":\"What is the practical implication of probabilistic convection triggering?\",\"answer\":\"The results suggest probabilistic machine learning models can act as stochastic parameterizations, improving how and when convection occurs in future weather and climate models and potentially reducing forecast and projection errors.\"}]","Characterizing uncertainty in deep convection triggering using explainable machine learning | PDF",1785683515,98,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"characterizing-uncertainty-in-deep-convection-triggering-using-explainable-machine-learning","",{"@graph":36,"@context":77},[37,54,68],{"@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/characterizing-uncertainty-in-deep-convection-triggering-using-explainable-machine-learning/118416/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What is the practical implication of probabilistic convection triggering?","Question",{"text":75,"@type":76},"The results suggest probabilistic machine learning models can act as stochastic parameterizations, improving how and when convection occurs in future weather and climate models and potentially reducing forecast and projection errors.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]