{"id":134491,"date":"2024-12-07T22:05:49","date_gmt":"2024-12-07T15:05:49","guid":{"rendered":"https:\/\/hotvideos24.online\/?p=134491"},"modified":"2024-12-07T22:05:49","modified_gmt":"2024-12-07T15:05:49","slug":"googles-ai-weather-prediction-model-is-pretty-darn-good","status":"publish","type":"post","link":"https:\/\/hotvideos24.online\/?p=134491","title":{"rendered":"Google\u2019s AI weather prediction model is pretty darn good"},"content":{"rendered":"<p> <script async src=\"https:\/\/pagead2.googlesyndication.com\/pagead\/js\/adsbygoogle.js?client=ca-pub-3711241968723425\"\r\n     crossorigin=\"anonymous\"><\/script>\r\n<ins class=\"adsbygoogle\"\r\n     style=\"display:block\"\r\n     data-ad-format=\"fluid\"\r\n     data-ad-layout-key=\"-fb+5w+4e-db+86\"\r\n     data-ad-client=\"ca-pub-3711241968723425\"\r\n     data-ad-slot=\"7910942971\"><\/ins>\r\n<script>\r\n     (adsbygoogle = window.adsbygoogle || []).push({});\r\n<\/script><br \/>\n<\/p>\n<div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">GenCast, a new AI model from Google DeepMind, is accurate enough to compete with traditional weather forecasting. It managed to outperform a leading forecast model when tested on data from 2019, according to recently published research. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">AI isn\u2019t going to replace traditional forecasting anytime soon, but it could add to the arsenal of tools used to predict the weather and warn the public about severe storms. GenCast is one of several AI weather forecasting <a href=\"https:\/\/www.technologyreview.com\/2024\/12\/04\/1107892\/google-deepminds-new-ai-model-is-the-best-yet-at-weather-forecasting\/\">models being developed<\/a> that might lead to more accurate forecasts.<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component clear-both block md:float-left md:mr-30 md:w-[320px] lg:-ml-100\">\n<div class=\"duet--article--article-pullquote mb-20\">\n<p class=\"duet--article--dangerously-set-cms-markup relative bg-repeating-lines-dark bg-[length:1px_1.2em] pb-8 font-polysans text-28 font-medium leading-120 tracking-1 selection:bg-franklin-20  dark:bg-repeating-lines-light dark:text-white dark:selection:bg-blurple\">GenCast is one of several AI weather forecasting models that might lead to more accurate forecasts<\/p>\n<\/div>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">\u201cWeather basically touches every aspect of our lives &#8230; it\u2019s also one of the big scientific challenges, predicting the weather,\u201d says Ilan Price, a senior research scientist at DeepMind. \u201cGoogle DeepMind has a mission to advance AI for the benefit of humanity. And I think this is one important way, one important contribution on that front.\u201d<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Price and his colleagues tested GenCast against the ENS system, one of the world\u2019s top-tier models for forecasting that\u2019s run by the European Centre for Medium-Range Weather Forecasts (<a href=\"https:\/\/www.ecmwf.int\/\">ECMWF<\/a>). GenCast outperformed ENS 97.2 percent of the time, according to research <a href=\"https:\/\/www.nature.com\/articles\/s41586-024-08252-9\">published this week in the journal <em>Nature<\/em><\/a>. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">GenCast is a machine learning weather prediction model trained on weather data from 1979 to 2018. The model learns to recognize patterns in the four decades of historical data and uses that to make predictions about what might happen in the future. That\u2019s very different from how traditional models like ENS work, which still rely on supercomputers to solve complex equations in order to simulate the physics of the atmosphere. Both GenCast and ENS produce <a href=\"https:\/\/www.metoffice.gov.uk\/research\/weather\/ensemble-forecasting\/what-is-an-ensemble-forecast\">ensemble forecasts<\/a>, which offer a range of possible scenarios.<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">When it comes to predicting the path of a tropical cyclone, for example, GenCast was able to give an additional 12 hours of advance warning on average. GenCast was generally better at predicting cyclone tracks, extreme weather, and wind power production up to 15 days in advance.<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component clear-both block\">\n<div class=\"my-9\">\n<p><figcaption class=\"duet--article--dangerously-set-cms-markup inline text-gray-13 dark:text-gray-e9 [&amp;&gt;a:hover]:text-black [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-e9 dark:[&amp;&gt;a:hover]:shadow-underline-gray-63 [&amp;&gt;a]:shadow-underline-gray-13 dark:[&amp;&gt;a]:shadow-underline-gray-63\">An ensemble forecast from GenCast shows a range of possible storm tracks for Typhoon Hagibis, which become more accurate as the cyclone draws closer to the coast of Japan.<\/figcaption><cite class=\"duet--article--dangerously-set-cms-markup inline not-italic text-gray-63 dark:text-gray-bd [&amp;&gt;a:hover]:text-gray-63 [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-bd dark:[&amp;&gt;a:hover]:shadow-underline-gray [&amp;&gt;a]:shadow-underline-gray-63 dark:[&amp;&gt;a]:text-gray-bd dark:[&amp;&gt;a]:shadow-underline-gray\">Image: Google<\/cite><\/p>\n<\/div>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">One caveat is that GenCast tested itself against an older version of ENS, which now operates at a higher resolution. The peer-reviewed research compares GenCast predictions to ENS forecasts for 2019, seeing how close each model got to real-world conditions that year. The ENS system has improved significantly since 2019, according to ECMWF machine learning\u00a0coordinator\u00a0Matt Chantry. That makes it difficult to say how well GenCast might perform against ENS today. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">To be sure, resolution isn\u2019t the only important factor when it comes to making strong predictions. ENS was already working at a slightly higher resolution than GenCast in 2019, and GenCast still managed to beat it. DeepMind says it conducted similar studies on data from 2020 to 2022 and found similar results, although that hasn\u2019t been peer-reviewed. But it didn\u2019t have the data to make comparisons for 2023, when ENS started running at a significantly higher resolution.<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Dividing the world into a grid, GenCast operates at 0.25 degree resolution \u2014 meaning each square on that grid is a\u00a0quarter degree latitude by quarter degree longitude. ENS, in comparison, used 0.2 degree resolution in 2019 and is at 0.1 degree resolution now. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Nevertheless, the development of GenCast \u201cmarks a significant milestone in the evolution of weather forecasting,\u201d Chantry said in an emailed statement. Alongside ENS, the ECMWF says it\u2019s also running its own version of a <a href=\"https:\/\/charts.ecmwf.int\/products\/aifs_opencharts_meteogram?base_time=202412020000&amp;epsgram=aifs_classical_10d&amp;lat=51.4333&amp;lon=-1.0&amp;station_name=Reading\">machine learning system<\/a>. Chantry says it \u201ctakes some inspiration from GenCast.\u201d<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Speed is an advantage for GenCast. It can produce one 15-day forecast in just eight minutes using a single Google Cloud TPU v5. Physics-based models like ENS might need several hours to do the same thing. GenCast bypasses all the equations ENS has to solve, which is why it takes less time and computational power to produce a forecast. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">\u201cComputationally, it\u2019s orders of magnitude more expensive to run traditional forecasts compared to a model like Gencast,\u201d Price says.<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">That efficiency might ease some of the concerns about the environmental impact of <a href=\"https:\/\/www.theverge.com\/2024\/1\/24\/24049047\/data-center-ai-crypto-bitcoin-mining-electricity-report-iea\">energy-hungry AI data centers<\/a>, which have already <a href=\"https:\/\/www.theverge.com\/2024\/7\/2\/24190874\/google-ai-climate-change-carbon-emissions-rise\">contributed to Google\u2019s greenhouse gas emissions climbing in recent years<\/a>. But it\u2019s hard to suss out how GenCast compares to physics-based models when it comes to sustainability without knowing how much energy is used to train the machine learning model. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">There are still improvements GenCast can make, including potentially scaling up to a higher resolution. Moreover, GenCast puts out predictions at 12-hour intervals compared to traditional models that typically do so in shorter intervals. That can make a difference for how these forecasts can be used in the real world (to assess how much wind power will be available, for instance). <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component clear-both block md:float-left md:mr-30 md:w-[320px] lg:-ml-100\">\n<div class=\"duet--article--article-pullquote mb-20\">\n<p class=\"duet--article--dangerously-set-cms-markup relative bg-repeating-lines-dark bg-[length:1px_1.2em] pb-8 font-polysans text-28 font-medium leading-120 tracking-1 selection:bg-franklin-20  dark:bg-repeating-lines-light dark:text-white dark:selection:bg-blurple\">\u201cWe\u2019re kind of wrapping our heads around, is this good? And why?\u201d<\/p>\n<\/div>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">\u201cYou would want to know what the wind is going to be doing throughout the day, not just at 6AM and 6PM,\u201d says Stephen Mullens, an assistant instructional professor of meteorology\u00a0at the University of\u00a0Florida who was not involved in the GenCast research. <\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">While there\u2019s growing interest in how AI can be used to improve forecasts, it still has to prove itself. \u201cPeople are looking at it. I don\u2019t think that the meteorological community as a whole is bought and sold on it,\u201d Mullens says. \u201cWe are trained scientists who think in terms of physics &#8230; and because AI fundamentally isn\u2019t that, then there\u2019s still an element where we\u2019re kind of wrapping our heads around, is this good? And why?\u201d<\/p>\n<\/div>\n<div class=\"duet--article--article-body-component\">\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Forecasters can check out GenCast for themselves; DeepMind released the\u00a0<a href=\"https:\/\/github.com\/google-deepmind\/graphcast\">code<\/a> for its open-source model. Price says he sees GenCast and more improved AI models being used in the real world alongside traditional models. \u201cOnce these models get into the hands of practitioners, it further builds trust and confidence,\u201d Price says. \u201cWe really want this to have a kind of widespread social impact.\u201d<\/p>\n<\/div>\n<\/div>\n<p><script async src=\"https:\/\/pagead2.googlesyndication.com\/pagead\/js\/adsbygoogle.js?client=ca-pub-3711241968723425\"\r\n     crossorigin=\"anonymous\"><\/script>\r\n<ins class=\"adsbygoogle\"\r\n     style=\"display:block\"\r\n     data-ad-format=\"fluid\"\r\n     data-ad-layout-key=\"-fb+5w+4e-db+86\"\r\n     data-ad-client=\"ca-pub-3711241968723425\"\r\n     data-ad-slot=\"7910942971\"><\/ins>\r\n<script>\r\n     (adsbygoogle = window.adsbygoogle || []).push({});\r\n<\/script><br \/>\n<br \/><div data-type=\"_mgwidget\" data-widget-id=\"1660802\">\r\n<\/div>\r\n<script>(function(w,q){w[q]=w[q]||[];w[q].push([\"_mgc.load\"])})(window,\"_mgq\");\r\n<\/script>\r\n<br \/>\n<br \/><a href=\"https:\/\/www.theverge.com\/2024\/12\/7\/24314064\/ai-weather-forecast-model-google-deepmind-gencast\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>GenCast, a new AI model from Google DeepMind, is accurate enough to compete with traditional weather forecasting. It managed to outperform a leading forecast model when tested on data from &hellip; <a href=\"https:\/\/hotvideos24.online\/?p=134491\" class=\"more-link\">Read More<\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[],"class_list":["post-134491","post","type-post","status-publish","format-standard","hentry","category-business","entry"],"_links":{"self":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts\/134491","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=134491"}],"version-history":[{"count":0,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=\/wp\/v2\/posts\/134491\/revisions"}],"wp:attachment":[{"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=134491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=134491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hotvideos24.online\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=134491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}