{"id":16166,"date":"2024-07-23T09:03:18","date_gmt":"2024-07-23T01:03:18","guid":{"rendered":"https:\/\/www.1ai.net\/?p=16166"},"modified":"2024-07-23T09:03:18","modified_gmt":"2024-07-23T01:03:18","slug":"%e8%b0%b7%e6%ad%8c%e5%8f%91%e5%b8%83-neuralgcm-%e5%a4%a9%e6%b0%94%e9%a2%84%e6%8a%a5-ai-%e6%a8%a1%e5%9e%8b%ef%bc%9a%e8%bf%90%e8%a1%8c%e6%88%90%e6%9c%ac%e6%9b%b4%e4%bd%8e%e3%80%81%e9%a2%84%e6%b5%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/16166.html","title":{"rendered":"Google releases NeuralGCM weather forecast AI model: lower operating costs and more accurate forecasts"},"content":{"rendered":"<p data-vmark=\"e2be\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%b0%b7%e6%ad%8c\" title=\"[View articles tagged with [Google]]\" target=\"_blank\" >Google<\/a>The company's latest release is the new NeuralGCM <a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [AI models]]\" target=\"_blank\" >AI Models<\/a>that combines machine learning and traditional techniques to build new <a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e5%a4%a9%e6%b0%94%e9%a2%84%e6%b5%8b%e6%a8%a1%e5%9e%8b\" title=\"[SEES ARTICLES WITH [AI WEATHER PREDICTION MODEL] LABELS]\" target=\"_blank\" >AI weather prediction model<\/a>,<strong>The results were published yesterday in<a href=\"https:\/\/www.nature.com\/articles\/s41586-024-07744-y\" target=\"_blank\" rel=\"noopener\">Nature<\/a>Journals<\/strong>.<\/p>\n<p data-vmark=\"950b\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-16167\" title=\"10b234ce-faae-4838-ac89-273b7b2652e5\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/10b234ce-faae-4838-ac89-273b7b2652e5.jpg\" alt=\"10b234ce-faae-4838-ac89-273b7b2652e5\" width=\"800\" height=\"366\" \/><\/p>\n<p data-vmark=\"e5c8\">Google says NeuralGCM is characterized by lower cost and higher accuracy in forecasting weather 1-10 days into the future than other weather forecasting models based purely on machine learning.<\/p>\n<p data-vmark=\"fa7d\">The NeuralGCM model is open source and can be run relatively quickly by users on laptops, says study co-author Stephen Hoyer of Google Research.<\/p>\n<p data-vmark=\"0a94\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-16168\" title=\"611aaea6-09f5-42b0-95ca-69d7cfc565ae\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/611aaea6-09f5-42b0-95ca-69d7cfc565ae.jpg\" alt=\"611aaea6-09f5-42b0-95ca-69d7cfc565ae\" width=\"800\" height=\"461\" \/><\/p>\n<p data-vmark=\"96a3\">The NeuralGCM model was developed by Google Research, Google <a href=\"https:\/\/www.1ai.net\/en\/tag\/deepmind\" title=\"_Other Organiser\" target=\"_blank\" >DeepMind<\/a>Scientists at MIT, Harvard University and the European Center for Medium-Range Weather Forecasts (ECMWF) have developed it using machine learning and neural networks, and IT Home has attached its training model below:<\/p>\n<ul class=\"medium-size list-paddingleft-2\">\n<li>\n<p data-vmark=\"531b\">Using brain neurons as a model, trained on weather data from the past few decades.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"2256\">It also uses physical equations to describe large-scale weather patterns, essentially combining GCMs, physics-intensive methods with AI-driven tasks.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"893f\">Some large-scale physics was retained and artificial intelligence was used to replace some of the modeling.<\/p>\n<\/li>\n<\/ul>\n<p data-vmark=\"919e\">The result, the researchers say, is that the model can make high-quality forecasts faster with less computing power. They say NeuralGCM is as accurate as the European Center for Medium-Range Weather Forecasts (ECMWF) 1-15 day forecasts.<\/p>\n<p data-vmark=\"19b8\"><span class=\"referenceTitle\">Attach reference address<\/span><\/p>\n<ul class=\"custom_reference list-paddingleft-1\">\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"911b\"><a href=\"https:\/\/www.nature.com\/articles\/s41586-024-07744-y\" target=\"_blank\" rel=\"noopener\">Neural general circulation models for weather and climate<\/a><\/p>\n<\/li>\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"82a9\"><a href=\"https:\/\/www.axios.com\/2024\/07\/22\/google-ai-weather-climate-forecast-model\" target=\"_blank\" rel=\"noopener\">New Google AI weather and climate model improves accuracy<\/a><\/p>\n<\/li>\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"c1bf\"><a href=\"https:\/\/www.technologyreview.com\/2024\/07\/22\/1095184\/a-new-weather-prediction-model-from-google-combines-ai-with-traditional-physics\/\" target=\"_blank\" rel=\"noopener\">Google's new weather prediction system combines AI with traditional physics<\/a><\/p>\n<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>Google has released a new AI model called NeuralGCM, which combines machine learning and traditional techniques to build a new AI weather prediction model, the results of which were published in the journal Nature yesterday. Google says NeuralGCM is characterized by lower cost and higher accuracy in predicting weather 1-10 days into the future than other weather forecasting models based purely on machine learning. Study co-author Stephen Hoyer of Google Research said the NeuralGCM model is open source and can be run relatively quickly on a laptop computer. The NeuralGCM model was developed by Google Research, Google DeepMin<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3661,167,593,281],"collection":[],"class_list":{"0":"post-16166","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-news","7":"tag-ai","9":"tag-deepmind","10":"tag-281"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16166","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=16166"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16166\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=16166"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=16166"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=16166"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=16166"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}