[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126112-en":3,"doc-seo-126112-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126112,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Improving forecasts of precipitation extremes over northern and central Italy using machine learning - Research Article","Accurate prediction of intense precipitation events is a key goal for operational weather services, especially as global warming amplifies extremes. While numerical weather prediction and dynamical ensembles provide uncertainty estimates, direct precipitation forecasting remains difficult due to precipitation’s intermittent and highly variable nature. This work presents a hybrid machine-learning chain, MaLCoX, built on a random-forest pipeline to recognize favourable synoptic conditions and classify extreme precipitation types for northern and central Italy. Trained on high-resolution precipitation truth data with ECMWF reforecast predictors, it improves probabilistic medium-range accuracy after sufficient training and adds a physical diagnostic for forecasters.","Received: 29 June 2023 Revised: 3 April 2024 Accepted: 22 April 2024  \nDOI: 10.1002/qj.4755  \nRESEAR CH ARTICLE  \nImproving forecasts of precipitation extremes over northern and central Italy using machine learning  \nFederico Grazzini1,2  Joshua Dorrington3  Christian M. Grams3 George C. Craig1  Linus Magnusson4  Frederic Vitart4  \n1 Ludwig-Maximilians-Universität, Meteorologisches Institut, Munich, Germany  \n2Arpae-SIMC, Regione Emilia-Romagna, Bologna, Italy  \n3 Department Troposphere Research, Institute of Meteorology and Climate Research (IMKTRO), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany  \n4 ECMWF, Reading, UK  \nCorrespondence  \nFederico Grazzini, Meteorologisches Institut, Ludwig-Maximilians-Universität, München, 80333, Germany.  \nEmail: federico.grazzini@lmu.de  \nFunding information  \nDeutsche Forschungsgemeinschaft; Helmholtz Young Investigator Group‘Sub-Seasonal Predictability:  \nUnderstanding the Role of Diabatic Outflow (SPREADOUT)’, Grant/Award Number: VH-NG-1243  \nAbstract  \nThe accurate prediction of intense precipitation events is one of the main objectives of operational weather services. This task is even more relevant nowadays, with the rapid progression of global warming which intensifies these events. Numerical weather prediction models have improved continuously over time, providing uncertainty estimation with dynamical ensembles. However, direct precipitation forecasting is still challenging. Greater availability of machine-learning tools paves the way to a hybrid forecasting approach, with the optimal combination of physical models, event statistics, and user-oriented postprocessing. Here we describe a specific chain, based on a random-forest (RF) pipeline, specialised in recognising favourable synoptic conditions leading to precipitation extremes and subsequently classifying extremes into predefined types. The application focuses on northern and central Italy, taken as a testbed region, but is seamlessly extensible to other regions and time-scales. The system is called MaLCoX (Machine Learning model predicting Conditions for eXtreme precipitation) and is running daily at the Italian regional weather service of ARPAE Emilia-Romagna. MalCoX has been trained with the ARCIS gridded high-resolution precipitation dataset as the target truth, using the last 20 years of the European Centre for Medium-Range Weather Forecasts (ECMWF) reforecast dataset as input predictors. We show that, with a long enough training period, the optimal blend of larger-scale information with direct model output improves the probabilistic forecast accuracy of extremes in the medium range. In addition, with specific methods, we provide a useful diagnostic to convey to forecasters the underlying physical storyline which makes a meteorological event extreme.  \nKEYW O RDS  \nextreme precipitation, hybrid forecast model, large-scale precursors, machine learning, northern Italy, predictability, warning chain  \nThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.  \n© 2024 The Authors. Quarterly Journal of the Royal Meteorological Society published by John Wiley & Sons Ltd on behalf of Royal Meteorological Society.  \n2  \nGRAZZINI et al.  \n1  INTRODUCTION  \nItaly is among the European nations most exposed to torrential rainfall and flash flooding, due to its geographical conformation and climatological characteristics (Grazzini, 2021) . Every year these weather hazards produce huge costs and deadly consequences. The correct prediction of intense meteorological phenomena isone of the main objectives of operational weather services, and this task is even more relevant today with the rapid progression of global warming which amplifies extremes (Seneviratne et al., 2021; Tramblay & Somot, 2018) . Numerical weather prediction (NWP)","cbCaivy96DWwW62H","https://ap.wps.com/l/cbCaivy96DWwW62H","pdf",13421727,6,1,15,"English","en",105,"# Abstract\n# Introduction\n## Operational forecasting challenges and global warming context\n## Limits of direct precipitation predictability\n## Motivation for machine learning postprocessing\n## Link between Mediterranean extreme precipitation and large-scale flow\n## The MaLCoX random-forest postprocessing chain","[{\"question\":\"What problem does the MaLCoX system address?\",\"answer\":\"It improves forecasting of precipitation extremes by combining large-scale predictors with direct model output and by recognizing synoptic conditions that lead to extreme events.\"},{\"question\":\"How is MaLCoX implemented in this study?\",\"answer\":\"MaLCoX uses a random-forest (RF) pipeline that first identifies favourable synoptic conditions and then classifies extremes into predefined types.\"},{\"question\":\"What data are used to train and evaluate the model?\",\"answer\":\"The model is trained using the ARCIS gridded high-resolution precipitation dataset as target truth and uses the last 20 years of ECMWF reforecast data as input predictors.\"}]","Improving forecasts of precipitation extremes over northern and central Italy using machine learning - Research Article | PDF",1785903229,38,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"improving-forecasts-of-precipitation-extremes-over-northern-and-central-italy-using-machine-learning-research-article","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/improving-forecasts-of-precipitation-extremes-over-northern-and-central-italy-using-machine-learning-research-article/126112/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the MaLCoX system address?","Question",{"text":77,"@type":78},"It improves forecasting of precipitation extremes by combining large-scale predictors with direct model output and by recognizing synoptic conditions that lead to extreme events.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How is MaLCoX implemented in this study?",{"text":82,"@type":78},"MaLCoX uses a random-forest (RF) pipeline that first identifies favourable synoptic conditions and then classifies extremes into predefined types.",{"name":84,"@type":75,"acceptedAnswer":85},"What data are used to train and evaluate the model?",{"text":86,"@type":78},"The model is trained using the ARCIS gridded high-resolution precipitation dataset as target truth and uses the last 20 years of ECMWF reforecast data as input predictors.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]