{"id":16312,"date":"2025-04-22T04:01:13","date_gmt":"2025-04-22T04:01:13","guid":{"rendered":"http:\/\/TheNextWeb=1413170"},"modified":"2025-04-22T04:01:13","modified_gmt":"2025-04-22T04:01:13","slug":"esa-and-ibm-launch-ai-model-with-intuitive-understanding-of-earth","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=16312","title":{"rendered":"ESA and IBM launch AI model with \u2018intuitive\u2019 understanding of Earth"},"content":{"rendered":"\n<div><img decoding=\"async\" src=\"https:\/\/img-cdn.tnwcdn.com\/image\/tnw-blurple?filter_last=1&amp;fit=1280%2C640&amp;url=https%3A%2F%2Fcdn0.tnwcdn.com%2Fwp-content%2Fblogs.dir%2F1%2Ffiles%2F2025%2F04%2FUntitled-design-27.jpg&amp;signature=9a6ac8b3412c19e64b8cb2b91065c4ae\" class=\"ff-og-image-inserted\"><\/div>\n<p><span>IBM and the European Space Agency (ESA) today launched TerraMind, a new open-source AI model with an \u201cintuitive\u201d understanding of Earth. According to the research team, the system is the best-performing AI model for Earth observation.<\/span><\/p>\n<p><span>In an ESA-led evaluation, TerraMind beat 12 leading AI models on the PANGAEA benchmark \u2014 a community standard for Earth observation. The model excelled at various real-world tasks, including land cover classification, change detection, and multi-sensor analysis. On average, it outperformed other models by 8% or more.<\/span><\/p>\n<p>\u201cTo me, what sets TerraMind apart is its ability to go beyond simply processing earth observations with computer vision algorithms,\u201d said Juan Bernab\u00e9-Moreno, director of IBM Research UK and Ireland. \u201cIt instead has an intuitive understanding of geospatial data and our planet.\u201d<\/p>\n<p><span>TerraMind is a generative AI model that can understand different types of data \u2014 such as images, text, and time-based sequences (like climate patterns) \u2014 and spot connections between these different kinds of information. That\u2019s particularly useful when dealing with an immensely complex system like Earth.&nbsp;&nbsp;<\/span><\/p>\n<div class=\"inarticle-wrapper channel-cta\">\n<div class=\"ica-text\" readability=\"0\"><a href=\"https:\/\/thenextweb.com\/conference\/schedule?utm_source=google&amp;utm_medium=display&amp;utm_campaign=global_tnw_media_event-registration_prospecting_offer_2025-tnw-conference-amsterdam&amp;utm_term=in-article-springsale\" data-event-category=\"Article\" data-event-action=\"In Article Block\" data-event-label=\"From Shark Tank to Tinder Swindler\" target=\"_blank\" readability=\"6\" rel=\"noopener\"><\/p>\n<p class=\"ica-text__title\">From Shark Tank to Tinder Swindler<\/p>\n<p>TNW Conference 2025 combines the latest breakthroughs in tech, the startup ecosystem &amp; enterprise innovation<\/p>\n<p><\/a><\/div>\n<\/div>\n<p><span>The model was trained on 9 million samples drawn from nine different data types, including satellite images, climate records, terrain features, and vegetation maps. The broad dataset covered every region and biome on Earth. It was designed to minimise bias and ensure the model can be used reliably across the globe, the researchers said.&nbsp;<\/span><\/p>\n<h2>ESA and IBM expand AI\u2019s push into climate modelling<\/h2>\n<p><span>TerraMind is built on Prithvi, an open-source family of foundational climate models launched by IBM and NASA in 2023. The Prithvi models require relatively less computational power than traditional climate modelling software, making them potentially more environmentally friendly.<\/span><\/p>\n<p><span>A standout feature of TerraMind is its \u201cThinking-in-Modalities\u201d (TiM) tuning. Similar to <\/span><a href=\"https:\/\/www.techtarget.com\/searchenterpriseai\/definition\/chain-of-thought-prompting#:~:text=Chain%2Dof%2Dthought%20(CoT,way%20that%20mimics%20human%20reasoning.\" target=\"_blank\" rel=\"nofollow noopener\"><span>chain-of-thought reasoning<\/span><\/a><span> in language models, TiM lets TerraMind self-generate extra data to improve its performance.&nbsp;<\/span><\/p>\n<p><span>\u201cTiM tuning boosts data efficiency by self-generating the additional training <a href=\"https:\/\/thenextweb.com\/topic\/data\" target=\"_blank\" rel=\"noopener\">data<\/a> relevant to the problem being addressed \u2014 for example, by telling the model to \u2018think\u2019 about land cover when mapping water bodies,\u201d said Johannes Jakubik, an IBM research scientist based in Zurich.&nbsp;<\/span><\/p>\n<p><span>TerraMind was built in collaboration with Polish spacetech firm KP Labs, the J\u00fclich Supercomputing Centre in Germany, and the German Space Agency (DLR). The model is now available open-source on Hugging Face. Fine-tuned versions will be released in the coming months.&nbsp;<\/span><\/p>\n<p><span>ESA, NASA, and IBM are by no means the only organisations experimenting with <a href=\"https:\/\/thenextweb.com\/topic\/artificial-intelligence\" target=\"_blank\" rel=\"noopener\">AI<\/a> models for climate forecasting. Another example emerged from Google DeepMind, which recently unveiled an <\/span><a href=\"https:\/\/thenextweb.com\/news\/google-deepminds-new-ai-weather-forecaster-gencast\" target=\"_blank\" rel=\"noopener\"><span>AI weather forecaster<\/span><\/a><span> that <\/span><span>makes faster and more accurate predictions than the best system available today. <\/span><\/p>\n<p><span>The EU has also experimented with the tech. Last year, the union unveiled a comprehensive <\/span><a href=\"https:\/\/thenextweb.com\/news\/eu-launches-ai-powered-digital-twin-of-the-earth\" target=\"_blank\" rel=\"noopener\"><span>digital twin of the Earth<\/span><\/a><span> that uses vast troves of data to improve climate predictions.<\/span><\/p>\n<p> <a href=\"https:\/\/thenextweb.com\/news\/esa-ibm-launch-ai-model-with-intuitive-understanding-of-earth\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>IBM and the European Space Agency (ESA) today launched TerraMind, a new open-source AI model with an \u201cintuitive\u201d understanding of Earth. According to the research team, the system is the best-performing AI&#8230;<\/p>\n","protected":false},"author":1,"featured_media":16313,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/16312"}],"collection":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=16312"}],"version-history":[{"count":0,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/16312\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/media\/16313"}],"wp:attachment":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16312"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16312"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16312"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}