[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120986-en":3,"doc-seo-120986-105":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},120986,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Machine Learning for Stochastic Parametrisation","Atmospheric weather and climate models are built on deterministic formulations, where sub-grid forcing is estimated from resolved variables to evolve large-scale flow. Limited scale separation introduces major forecast error, motivating stochastic techniques that represent uncertainty in small-scale processes across multiple timescales. Alongside this, machine learning progress enables replacing parametrisation schemes, promising faster and more accurate simulations. This position paper connects stochastic parametrisation and ML and examines early probabilistic, data-driven directions and remaining challenges.","arXiv :2402 .09471v1 [ cs .LG] 12 Feb 2024  \nMachine Learning for Stochastic Parametrisation  \nHannah M. Christensen, Salah Kouhen, Greta Miller, Atmospheric, Oceanic and Planetary Physics, Dept. of Physics, University of Oxford, Oxford OX1 3PU, UK  \nand Raghul Parthipan  \nDept. of Computer Science, University of Cambridge, Cambridge, CB3 0FD, UK,  \nand British Antarctic Survey, Cambridge, CB3 0ET, UK  \n[Hannah.Christensen@physics.ox.ac.uk](Hannah.Christensen@physics.ox.ac.uk)  \nFebruary 16, 2024  \nAbstract  \nAtmospheric models used for weather and climate prediction are traditionally formulated in a deterministic manner. In other words, given a particular state of theresolved scale variables, the most likely forcing from the sub-grid scale processes is estimated and used to predict the evolution of the large-scale flow. However, the lack of scale-separation in the atmosphere means that this approach is a large source of error in forecasts. Over recent years, an alternative paradigm has developed: the use of stochastic techniques to characterise uncertainty in small-scale processes. These techniques are now widely used across weather, sub-seasonal, seasonal, and climate timescales. In parallel, recent years have also seen significant progress in replacing parametrisation schemes using machine learning (ML) . This has the potential to both speed up and improve our numerical models. However, the focus to date has largely been on deterministic approaches. In this position paper, we bring together these two key developments, and discuss the potential for data-driven approaches for stochastic parametrisation. We highlight early studies in this area, and draw attention to the novel challenges that remain.  \nKeywords: machine learning, stochastic parametrisation, uncertainty quantification, model  \nerror  \nImpact Statement  \nWeather and climate predictions are relied on by users from industry, charities, governments, and the general public. The largest source of uncertainty in these predictions arises from approximations made when building the computer model used to make them. In particular, the representation of small-scale processes such as clouds and thunderstorms is a large source of uncertainty because of their complexity and their unpredictability. Machine learning (ML) approaches, trained to mimic high-quality datasets, present an unparalleled opportunity to improve the representation of these small-scale processes in models. However, it is important to account for the unpredictability of these processes while doing so. In this paper, we demonstrate the untapped potential of such probabilistic ML approaches for improving weather and climate prediction.  \n1 Introduction  \nWeather and climate models exhibit long-standing biases in mean state, modes of variability, and the representation of extremes. These biases hinder progress across the World Climate Research Programme grand challenges. Understanding and reducing these biases is a key focus for the research community.  \nAt the heart of weather and climate models are the physical equations of motion which describe the atmosphere and ocean systems. To predict the evolution of the climate system, these equations are discretised in space and time. The resolution ranges from order 100 km and 30-60 minutes in a typical climate model, through 10 km and 5-10 minutes in global numerical weather prediction (NWP) models, to one km and a few tens of seconds for state-of-the-art convection permitting runs. The impact of unresolved scales of motion on the resolved scales is represented in models through parametrisation schemes (Christensen and Zanna, 20202) . Many of the biases in weather and climate models stem from the assumptions and approximations made during this parametrisation process (Hyder et al., 2018) . Furthermore, despite their approximate nature, conventional parametrisation schemes account for twice as much compute time as the dynamical core in a typical atmospheric model (We","cbCailFy5OJaPAKH","https://ap.wps.com/l/cbCailFy5OJaPAKH","pdf",2816480,1,20,"English","en",105,"# Abstract\n# Impact Statement\n# Introduction","[{\"question\":\"Why do traditional deterministic atmospheric parametrisation approaches create forecast errors?\",\"answer\":\"They rely on unresolved sub-grid processes being inferred from resolved-scale state, but limited scale separation makes this assumption a major error source in forecasts.\"},{\"question\":\"What does stochastic parametrisation add to weather and climate modeling?\",\"answer\":\"It represents uncertainty by drawing sub-grid tendencies from probability distributions conditioned on the resolved state, instead of using a single deterministic estimate.\"},{\"question\":\"How can machine learning improve parametrisation schemes in atmospheric models?\",\"answer\":\"Machine learning can emulate existing or more complex parametrisation components to speed up simulations and potentially increase accuracy, especially when trained on high-fidelity datasets.\"}]","Machine Learning for Stochastic Parametrisation | PDF",1785733193,50,{"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},"machine-learning-for-stochastic-parametrisation","",{"@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/machine-learning-for-stochastic-parametrisation/120986/",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},"Why do traditional deterministic atmospheric parametrisation approaches create forecast errors?","Question",{"text":76,"@type":77},"They rely on unresolved sub-grid processes being inferred from resolved-scale state, but limited scale separation makes this assumption a major error source in forecasts.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What does stochastic parametrisation add to weather and climate modeling?",{"text":81,"@type":77},"It represents uncertainty by drawing sub-grid tendencies from probability distributions conditioned on the resolved state, instead of using a single deterministic estimate.",{"name":83,"@type":74,"acceptedAnswer":84},"How can machine learning improve parametrisation schemes in atmospheric models?",{"text":85,"@type":77},"Machine learning can emulate existing or more complex parametrisation components to speed up simulations and potentially increase accuracy, especially when trained on high-fidelity datasets.","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},[94,98,102,106,111,115,120,123,127,130,134],{"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":29,"slug":114},6,"Technology","technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":21,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":21,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]