{"id":7644,"date":"2025-05-21T15:07:33","date_gmt":"2025-05-21T13:07:33","guid":{"rendered":"https:\/\/nyheter.ntnu.no\/?p=7644"},"modified":"2025-05-21T15:07:34","modified_gmt":"2025-05-21T13:07:34","slug":"improving-weather-forecasting-with-neural-networks","status":"publish","type":"post","link":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/","title":{"rendered":"Improving weather forecasting with neural networks"},"content":{"rendered":"\n

It all started at a conference, where a speaker from the UK Met Office discussed advancements in their models. With a background in climate science, James saw the potential for further improvements using neural networks.<\/p>\n\n\n

\n
\"portrettbilde
James Jackaman got his Marie Sk\u0142odowska-Curie Postdoctoral Fellowship in 2023 to improving weather forecasting.<\/figcaption><\/figure>\n<\/div>\n\n\n

\u201cIt\u2019s a reasonable approach, what they’re doing. But I felt like there were still some improvements which could be made,\u201d he says.<\/p>\n\n\n\n

This inspiration, combined with a desire to make a tangible impact, motivated him to pursue this innovative research direction and made it the target for his application for Marie Sk\u0142odowska-Curie Postdoctoral Fellowship (MSCA)<\/a>. A grant he got in 2023 as part of the Department of Mathematical Sciences at NTNU.  <\/a><\/p>\n\n\n\n

\u201cBecause it’s nice to sit down and prove things, but it’s also very nice to impact the world and make some positive changes,\u201d he said.<\/p>\n\n\n\n

Improving with neural network<\/h3>\n\n\n\n

\u201cTogether with my supervisor, Elena Celledoni, and collaborators from both academia and industry, we aim to improve weather forecasting using neural networks. Great strides have been made recently in weather forecasting with Google\u2019s GraphCast, which has proven a powerful and useful tool. Our approach differs in one key aspect though. We aim to use neural networks to enhance existing technologies as opposed to replacing them.\u201d  <\/p>\n\n\n\n

Higher simulation with limited area models<\/h3>\n\n\n\n

The challenge lies in the computational limitations that prevent global weather simulations at high resolutions. Weather forecasting has long involved many difficult-to-simulate phenomena (such as cloud coverage) and requires continuous integration with data through data assimilation. At its core, a forecasting model is driven by simulating fluid dynamics. And that\u2019s the crux here. \u201cTo obtain a locally accurate forecast, our simulation must be at a high resolution. Unfortunately, running the model at a high resolution makes the model runtime slower than real time, rendering the forecast obsolete. This has led us to consider a limited area model (LAM), which runs simulations at a higher resolution over a smaller region of interest, such as Northern Europe. This allows us to run at a higher resolution than possible with a global model, faster than real time,\u201d he said.<\/p>\n\n\n\n

\"\"
Weather Stations are quit accurate. Photo: Pixabay.<\/figcaption><\/figure>\n\n\n\n

Challenges with LAMs<\/h3>\n\n\n\n

There is one fundamental problem with LAMs: something called boundary conditions. When the model is restricted to a limited area, weather patterns need to be able to move into the area. Due to the atmosphere\u2019s multiscale nature, phenomena that occur at a fine resolution (such as vortices and eddies) will not appear on the poorly resolved global model.
\u201cIndeed, if our boundary data lacks these fine-grain phenomena, this will typically lead to unrealistic behavior near the boundaries of the LAM, polluting the simulation. We aim to bridge this gap with convolutional neural networks in a simplified setup. While still under development, we are now delving into the world of graph neural networks to move our approach to a more general setting,\u201d  he said.<\/p>\n\n\n\n

Support during the application process<\/h3>\n\n\n\n

The application process was demanding, requiring a detailed 10-page proposal. However, James was not alone in this endeavor.<\/p>\n\n\n\n

\u201cI received substantial support from the EU applications team at NTNU, as well as from my supervisor and colleagues. I think there’s a lot of support, and I was lucky in the sense that I knew these people already, because I\u2019ve just started in a position at NTNU. I would say that this collaborative effort was crucial in navigating the complexities of the application process and ultimately securing the grant. And if you’re trying to follow the academic track, then grant writing is incredibly important. Even applying and having a score that is not terrible, is meaningful for people who are looking to move up in the academic system,\u201d he said.<\/p>\n\n\n\n

Impact of improved models<\/h3>\n\n\n\n

The potential impact of this research is significant. Improved weather models can lead to better forecasting, which is crucial for various sectors, including agriculture, disaster management, and daily life.<\/p>\n\n\n\n

\u201cWhile the project is complex and may not yield a fully operational model within its current scope, it lays the groundwork for future advancements in meteorological simulations. And if this work is of interest to meteorological centers, this can be carried forward.<\/p>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

It all started at a conference, where a speaker from the UK Met Office discussed advancements in their models. With a background in climate science, James saw the potential for further improvements using neural networks. \u201cIt\u2019s a reasonable approach, what they’re doing. But I felt like there were still some improvements which could be made,\u201d he says. This […]<\/p>\n","protected":false},"author":96,"featured_media":7648,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1,3],"tags":[1094,1093,853],"theme":[752,878,944],"class_list":["post-7644","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-forskning","category-research","tag-matematikk-2","tag-msca-2","tag-trondheim-en","theme-natural-sciences","theme-research-communication","theme-science"],"acf":[],"yoast_head":"\nImproving weather forecasting with neural networks - NTNU Nyheter<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Improving weather forecasting with neural networks - NTNU Nyheter\" \/>\n<meta property=\"og:description\" content=\"It all started at a conference, where a speaker from the UK Met Office discussed advancements in their models. With a background in climate science, James saw the potential for further improvements using neural networks. \u201cIt\u2019s a reasonable approach, what they’re doing. But I felt like there were still some improvements which could be made,\u201d he says. This […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\" \/>\n<meta property=\"og:site_name\" content=\"NTNU Nyheter\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-21T13:07:33+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-21T13:07:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2000\" \/>\n\t<meta property=\"og:image:height\" content=\"1383\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"annelia@ntnu.no\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"annelia@ntnu.no\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\"},\"author\":{\"name\":\"annelia@ntnu.no\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/person\/91d693484488c376467de7d682cbd01d\"},\"headline\":\"Improving weather forecasting with neural networks\",\"datePublished\":\"2025-05-21T13:07:33+00:00\",\"dateModified\":\"2025-05-21T13:07:34+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\"},\"wordCount\":720,\"publisher\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#organization\"},\"image\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg\",\"keywords\":[\"matematikk\",\"MSCA\",\"Trondheim\"],\"articleSection\":[\"Forskning\",\"Research\"],\"inLanguage\":\"en\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\",\"url\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\",\"name\":\"Improving weather forecasting with neural networks - NTNU Nyheter\",\"isPartOf\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg\",\"datePublished\":\"2025-05-21T13:07:33+00:00\",\"dateModified\":\"2025-05-21T13:07:34+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#breadcrumb\"},\"inLanguage\":\"en\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage\",\"url\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg\",\"contentUrl\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg\",\"width\":2000,\"height\":1383,\"caption\":\"Weather forecasting is challenging to make 100%correct. Photo: Creative Commons.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Hjem\",\"item\":\"https:\/\/nyheter.ntnu.no\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Improving weather forecasting with neural networks\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#website\",\"url\":\"https:\/\/nyheter.ntnu.no\/en\/\",\"name\":\"NTNU Nyheter\",\"description\":\"Kunnskap for en bedre verden\",\"publisher\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/nyheter.ntnu.no\/en\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#organization\",\"name\":\"NTNU Nyheter\",\"url\":\"https:\/\/nyheter.ntnu.no\/en\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2023\/03\/logo-1.png\",\"contentUrl\":\"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2023\/03\/logo-1.png\",\"width\":512,\"height\":66,\"caption\":\"NTNU Nyheter\"},\"image\":{\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/person\/91d693484488c376467de7d682cbd01d\",\"name\":\"annelia@ntnu.no\",\"url\":\"https:\/\/nyheter.ntnu.no\/en\/author\/anneliantnu-no\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Improving weather forecasting with neural networks - NTNU Nyheter","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/","og_locale":"en_US","og_type":"article","og_title":"Improving weather forecasting with neural networks - NTNU Nyheter","og_description":"It all started at a conference, where a speaker from the UK Met Office discussed advancements in their models. With a background in climate science, James saw the potential for further improvements using neural networks. \u201cIt\u2019s a reasonable approach, what they’re doing. But I felt like there were still some improvements which could be made,\u201d he says. This […]","og_url":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/","og_site_name":"NTNU Nyheter","article_published_time":"2025-05-21T13:07:33+00:00","article_modified_time":"2025-05-21T13:07:34+00:00","og_image":[{"width":2000,"height":1383,"url":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg","type":"image\/jpeg"}],"author":"annelia@ntnu.no","twitter_card":"summary_large_image","twitter_misc":{"Written by":"annelia@ntnu.no","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#article","isPartOf":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/"},"author":{"name":"annelia@ntnu.no","@id":"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/person\/91d693484488c376467de7d682cbd01d"},"headline":"Improving weather forecasting with neural networks","datePublished":"2025-05-21T13:07:33+00:00","dateModified":"2025-05-21T13:07:34+00:00","mainEntityOfPage":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/"},"wordCount":720,"publisher":{"@id":"https:\/\/nyheter.ntnu.no\/en\/#organization"},"image":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage"},"thumbnailUrl":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg","keywords":["matematikk","MSCA","Trondheim"],"articleSection":["Forskning","Research"],"inLanguage":"en"},{"@type":"WebPage","@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/","url":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/","name":"Improving weather forecasting with neural networks - NTNU Nyheter","isPartOf":{"@id":"https:\/\/nyheter.ntnu.no\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage"},"image":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage"},"thumbnailUrl":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg","datePublished":"2025-05-21T13:07:33+00:00","dateModified":"2025-05-21T13:07:34+00:00","breadcrumb":{"@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#breadcrumb"},"inLanguage":"en","potentialAction":[{"@type":"ReadAction","target":["https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/"]}]},{"@type":"ImageObject","inLanguage":"en","@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#primaryimage","url":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg","contentUrl":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2025\/05\/weather-infographic-set_1284-5223-e1747832685127.jpg","width":2000,"height":1383,"caption":"Weather forecasting is challenging to make 100%correct. Photo: Creative Commons."},{"@type":"BreadcrumbList","@id":"https:\/\/nyheter.ntnu.no\/en\/improving-weather-forecasting-with-neural-networks\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Hjem","item":"https:\/\/nyheter.ntnu.no\/en\/"},{"@type":"ListItem","position":2,"name":"Improving weather forecasting with neural networks"}]},{"@type":"WebSite","@id":"https:\/\/nyheter.ntnu.no\/en\/#website","url":"https:\/\/nyheter.ntnu.no\/en\/","name":"NTNU Nyheter","description":"Kunnskap for en bedre verden","publisher":{"@id":"https:\/\/nyheter.ntnu.no\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/nyheter.ntnu.no\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en"},{"@type":"Organization","@id":"https:\/\/nyheter.ntnu.no\/en\/#organization","name":"NTNU Nyheter","url":"https:\/\/nyheter.ntnu.no\/en\/","logo":{"@type":"ImageObject","inLanguage":"en","@id":"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/logo\/image\/","url":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2023\/03\/logo-1.png","contentUrl":"https:\/\/nyheter.ntnu.no\/wp-content\/uploads\/2023\/03\/logo-1.png","width":512,"height":66,"caption":"NTNU Nyheter"},"image":{"@id":"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/nyheter.ntnu.no\/en\/#\/schema\/person\/91d693484488c376467de7d682cbd01d","name":"annelia@ntnu.no","url":"https:\/\/nyheter.ntnu.no\/en\/author\/anneliantnu-no\/"}]}},"_links":{"self":[{"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/posts\/7644","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/users\/96"}],"replies":[{"embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/comments?post=7644"}],"version-history":[{"count":4,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/posts\/7644\/revisions"}],"predecessor-version":[{"id":7654,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/posts\/7644\/revisions\/7654"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/media\/7648"}],"wp:attachment":[{"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/media?parent=7644"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/categories?post=7644"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/tags?post=7644"},{"taxonomy":"theme","embeddable":true,"href":"https:\/\/nyheter.ntnu.no\/en\/wp-json\/wp\/v2\/theme?post=7644"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}