{"id":360040,"date":"2025-01-01T17:13:27","date_gmt":"2025-01-01T16:13:27","guid":{"rendered":"https:\/\/climatescience.press\/?p=360040"},"modified":"2025-01-01T17:13:29","modified_gmt":"2025-01-01T16:13:29","slug":"claim-artificial-intelligence-can-improve-climate-models","status":"publish","type":"post","link":"https:\/\/climatescience.press\/?p=360040","title":{"rendered":"Claim: Artificial Intelligence can Improve Climate Models"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

<\/p>\n\n\n\n

From Watts Up With That?<\/a><\/p>\n\n\n\n

Essay by<\/strong> Eric Worrall<\/a><\/p>\n\n\n\n

If you have a possible missing variable problem, the solution is to add more arbitrary adjustments to your model?<\/p>\n\n\n\n

\n

AI Exposes Accelerated Climate Change: 3\u00b0C Temperature Rise Imminent<\/strong><\/p>\n\n\n\n

BY IOP PUBLISHING DECEMBER 28, 2024<\/p>\n\n\n\n

AI-enhanced research shows regional warming will exceed critical thresholds faster than expected, with most regions surpassing 1.5\u00b0C by 2040. Vulnerable areas like South Asia face heightened risks, urging swift adaptation actions.<\/p>\n\n\n\n

Three leading climate scientists have analyzed data from 10 global climate models, utilizing artificial intelligence (AI) to enhance accuracy. Their findings indicate that regional warming thresholds are likely to be reached sooner than previously estimated.<\/p>\n\n\n\n

\u2026<\/p>\n\n\n\n

Elizabeth Barnes says: \u201cOur research underscores the importance of incorporating innovative AI techniques like transfer learning into climate modeling to potentially improve and constrain regional forecasts and provide actionable insights for policymakers, scientists, and communities worldwide.\u201d

\u2026Read more:<\/p>\n\n\n\n

\u00a0https:\/\/scitechdaily.com\/ai-exposes-accelerated-climate-change-3c-temperature-rise-imminent\/<\/a><\/p>\n<\/blockquote>\n\n\n\n

The referenced study;<\/p>\n\n\n\n

\n

Combining climate models and observations to predict the time remaining until regional warming thresholds are reached<\/strong><\/p>\n\n\n\n

Elizabeth A Barnes*<\/sup>, Noah S Diffenbaugh and Sonia I Seneviratne<\/p>\n\n\n\n

Published 10 December 2024 \u2022 \u00a9 2024 The Author(s). Published by IOP Publishing Ltd
Environmental Research Letters<\/a>, Volume 20<\/a>, Number 1<\/a> Citation<\/strong> Elizabeth A Barnes et al<\/em> 2025 Environ. Res. Lett.<\/em> 20<\/strong> 014008DOI<\/strong> 10.1088\/1748-9326\/ad91ca<\/p>\n\n\n\n

Abstract<\/strong><\/p>\n\n\n\n

The importance of climate change for driving adverse climate impacts has motivated substantial effort to understand the rate and magnitude of regional climate change in different parts of the world. However, despite decades of research, there is substantial uncertainty in the time remaining until specific regional temperature thresholds are reached, with climate models often disagreeing both on the warming that has occurred to-date, as well as the warming that might be experienced in the next few decades. Here, we adapt a recent machine learning approach to train a convolutional neural network to predict the time (and its uncertainty) until different regional warming thresholds are reached based on the current state of the climate system. In addition to predicting regional rather than global warming thresholds, we include a transfer learning step in which the climate-model-trained network is fine-tuned with limited observations, which further improves predictions of the real world. Using observed 2023 temperature anomalies to define the current climate state, our method yields a central estimate of 2040 or earlier for reaching the 1.5 \u00b0C threshold for all regions where transfer learning is possible, and a central estimate of 2040 or earlier for reaching the 2.0 \u00b0C threshold for 31 out of 34 regions. For 3.0 \u00b0C, 26 \u00b0C out of 34 regions are predicted to reach the threshold by 2060. Our results highlight the power of transfer learning as a tool to combine a suite of climate model projections with observations to produce constrained predictions of future temperatures based on the current climate.Read more:\u00a0<\/p>\n\n\n\n

https:\/\/iopscience.iop.org\/article\/10.1088\/1748-9326\/ad91ca<\/a><\/p>\n<\/blockquote>\n\n\n\n

If I have understood correctly, they are essentially using the AI as a complex black box polynomial correction to their rather imprecise climate models, to try to squeeze out better answers. The polynomial is trained by comparing observed temperature data to model output, then the resultant amalgamation of climate models and AI polynomial corrections is extrapolated to try to predict future events.<\/p>\n\n\n\n

The problem with this approach is it creates the illusion of accuracy, without actually knowing if greater accuracy has been achieved<\/strong>. An AI used in this way applies complex arbitrary \u201ccorrections\u201d to input data, to generate a near perfect match to any data used to train that AI. But the AI knows nothing about the underlying physical phenomena. The AI might be able infer physical phenomena if it has enough data \u2013 or the AI could just make stuff up<\/strong>, especially if unknown critical input data is missing from the set of data which is used to train the AI.<\/p>\n\n\n\n

AI does have a role in scientific analysis. In fields like drug discovery and complex optimisation problems, AI can produce excellent results.<\/p>\n\n\n\n

But AI also has a well known tendency to go off the rails, to \u201challucinate\u201d false results.<\/p>\n\n\n\n

An AI malfunction is not a problem if you can test the quality of the AI results immediately. But using AI to try to figure out how to correct climate models, where nobody will know for years or decades whether the AI got it right, then using those AI corrections to project future events, this seems a dubious use of artificial intelligence.<\/p>\n\n\n\n

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

If you have a possible missing variable problem, the solution is to add more arbitrary adjustments to your model?<\/p>\n","protected":false},"author":121246920,"featured_media":360042,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","_crdt_document":"","advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"jetpack_post_was_ever_published":false},"categories":[1],"tags":[691822666,691818056,691818153],"class_list":{"0":"post-360040","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","6":"hentry","7":"category-uncategorized","8":"tag-artificial-intelligence-ai","9":"tag-climate-change","10":"tag-climate-models","12":"fallback-thumbnail"},"jetpack_publicize_connections":[],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/01\/0AI-Climate-1200x600-Article2-2.png?fit=1200%2C600&ssl=1","jetpack_likes_enabled":true,"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/paxLW1-1vF6","jetpack-related-posts":[{"id":405068,"url":"https:\/\/climatescience.press\/?p=405068","url_meta":{"origin":360040,"position":0},"title":"CCA: Artificial Intelligence is a Challenge to Climate Goals","author":"uwe.roland.gross","date":"26\/09\/2025","format":false,"excerpt":"How can a data center with co-located batteries be expected to compete against China\u2019s coal powered data centers, or the USA\u2019s gas- and nuclear-powered data centers?","rel":"","context":"In \"2035 Targets Advice\"","block_context":{"text":"2035 Targets Advice","link":"https:\/\/climatescience.press\/?tag=2035-targets-advice"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/09\/AQOAqzCCpYCpI6XNtng7SFR6DdxH4LIyML878RtRZQjWZqK_oZdfGU0DakI8ExMzFqUYKPuT9tx0F3kSpFZP5b4tJtuTsuvGto_DUSKKdpddci5ArZbvAMyApEdrMCQPs6UfhTH3tDMMoCeBCMojTYvUr94P.jpeg?fit=1200%2C1200&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/09\/AQOAqzCCpYCpI6XNtng7SFR6DdxH4LIyML878RtRZQjWZqK_oZdfGU0DakI8ExMzFqUYKPuT9tx0F3kSpFZP5b4tJtuTsuvGto_DUSKKdpddci5ArZbvAMyApEdrMCQPs6UfhTH3tDMMoCeBCMojTYvUr94P.jpeg?fit=1200%2C1200&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/09\/AQOAqzCCpYCpI6XNtng7SFR6DdxH4LIyML878RtRZQjWZqK_oZdfGU0DakI8ExMzFqUYKPuT9tx0F3kSpFZP5b4tJtuTsuvGto_DUSKKdpddci5ArZbvAMyApEdrMCQPs6UfhTH3tDMMoCeBCMojTYvUr94P.jpeg?fit=1200%2C1200&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/09\/AQOAqzCCpYCpI6XNtng7SFR6DdxH4LIyML878RtRZQjWZqK_oZdfGU0DakI8ExMzFqUYKPuT9tx0F3kSpFZP5b4tJtuTsuvGto_DUSKKdpddci5ArZbvAMyApEdrMCQPs6UfhTH3tDMMoCeBCMojTYvUr94P.jpeg?fit=1200%2C1200&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2025\/09\/AQOAqzCCpYCpI6XNtng7SFR6DdxH4LIyML878RtRZQjWZqK_oZdfGU0DakI8ExMzFqUYKPuT9tx0F3kSpFZP5b4tJtuTsuvGto_DUSKKdpddci5ArZbvAMyApEdrMCQPs6UfhTH3tDMMoCeBCMojTYvUr94P.jpeg?fit=1200%2C1200&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":293598,"url":"https:\/\/climatescience.press\/?p=293598","url_meta":{"origin":360040,"position":1},"title":"AI Researchers Pushing Their Value to Climate Activists","author":"uwe.roland.gross","date":"03\/01\/2024","format":false,"excerpt":"According to advocates, AI can generate better flood predictions than physics and geography. But is this just more magic box thinking?","rel":"","context":"In \"AI (artificial intelligence)\"","block_context":{"text":"AI (artificial intelligence)","link":"https:\/\/climatescience.press\/?tag=ai-artificial-intelligence-2"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0aiclimateban.jpg?fit=1200%2C643&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0aiclimateban.jpg?fit=1200%2C643&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0aiclimateban.jpg?fit=1200%2C643&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0aiclimateban.jpg?fit=1200%2C643&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0aiclimateban.jpg?fit=1200%2C643&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":287139,"url":"https:\/\/climatescience.press\/?p=287139","url_meta":{"origin":360040,"position":2},"title":"\u00a315 Million AI Climate Change Grant for the University of Southampton","author":"uwe.roland.gross","date":"08\/11\/2023","format":false,"excerpt":"Southampton will be at the forefront of government plans to make the UK a leading force for artificial intelligence after it was awarded millions of pounds.The University of Southampton has been given \u00a315m for a training centre aimed at developing artificial intelligence to tackle climate change. From Watts Up With\u2026","rel":"","context":"In \"AI (artificial intelligence)\"","block_context":{"text":"AI (artificial intelligence)","link":"https:\/\/climatescience.press\/?tag=ai-artificial-intelligence-2"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/11\/0image-20151103-16547-1kawsyc.webp?fit=1200%2C591&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/11\/0image-20151103-16547-1kawsyc.webp?fit=1200%2C591&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/11\/0image-20151103-16547-1kawsyc.webp?fit=1200%2C591&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/11\/0image-20151103-16547-1kawsyc.webp?fit=1200%2C591&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/11\/0image-20151103-16547-1kawsyc.webp?fit=1200%2C591&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":242672,"url":"https:\/\/climatescience.press\/?p=242672","url_meta":{"origin":360040,"position":3},"title":"AI`s Trained on Climate Models Predict Faster Warming","author":"uwe.roland.gross","date":"01\/02\/2023","format":false,"excerpt":"Using a simulation or model allows a large number of training runs to be packed into a short period of time, and constrains the output of the AI. But the AI is then tainted by the model, it effectively becomes an extension of the model.","rel":"","context":"Similar post","block_context":{"text":"Similar post","link":""},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/02\/image-23.png?fit=1200%2C800&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/02\/image-23.png?fit=1200%2C800&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/02\/image-23.png?fit=1200%2C800&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/02\/image-23.png?fit=1200%2C800&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2023\/02\/image-23.png?fit=1200%2C800&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":293843,"url":"https:\/\/climatescience.press\/?p=293843","url_meta":{"origin":360040,"position":4},"title":"Cyclone Jasper & BOM Forecasting \u2013 Getting to the Truth","author":"uwe.roland.gross","date":"05\/01\/2024","format":false,"excerpt":"For sure, it is difficult to forecast weather and climate, but the skill of new systems based on artificial intelligence (AI) show great improvement, while the Australian Bureau of Meteorology remains wedded to its General Circulation Models.","rel":"","context":"In \"Artificial Intelligence (AI)\"","block_context":{"text":"Artificial Intelligence (AI)","link":"https:\/\/climatescience.press\/?tag=artificial-intelligence-ai"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0IMG_2292.jpeg?fit=1200%2C648&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0IMG_2292.jpeg?fit=1200%2C648&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0IMG_2292.jpeg?fit=1200%2C648&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0IMG_2292.jpeg?fit=1200%2C648&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/01\/0IMG_2292.jpeg?fit=1200%2C648&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":350328,"url":"https:\/\/climatescience.press\/?p=350328","url_meta":{"origin":360040,"position":5},"title":"Natural Climate Change Factors","author":"uwe.roland.gross","date":"06\/11\/2024","format":false,"excerpt":"\u201cConsensus\u201d scientists do not believe that solar variability, internal climate variability (in this model simplified to the ~67-year stadium wave), or volcanism influence net global warming or climate change since 1750, yet considerable evidence exists that these factors have an impact. I\u2019ve previously built a model of the\u00a0HadCRUT5\u00a0global average temperature\u2026","rel":"","context":"In \"carbon dioxide (CO2)\"","block_context":{"text":"carbon dioxide (CO2)","link":"https:\/\/climatescience.press\/?tag=carbon-dioxide-co2"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/11\/00Screenshot-2024-11-06-163438.png?fit=1152%2C758&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/11\/00Screenshot-2024-11-06-163438.png?fit=1152%2C758&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/11\/00Screenshot-2024-11-06-163438.png?fit=1152%2C758&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/11\/00Screenshot-2024-11-06-163438.png?fit=1152%2C758&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/climatescience.press\/wp-content\/uploads\/2024\/11\/00Screenshot-2024-11-06-163438.png?fit=1152%2C758&ssl=1&resize=1050%2C600 3x"},"classes":[]}],"_links":{"self":[{"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/posts\/360040","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/users\/121246920"}],"replies":[{"embeddable":true,"href":"https:\/\/climatescience.press\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=360040"}],"version-history":[{"count":3,"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/posts\/360040\/revisions"}],"predecessor-version":[{"id":360044,"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/posts\/360040\/revisions\/360044"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/climatescience.press\/index.php?rest_route=\/wp\/v2\/media\/360042"}],"wp:attachment":[{"href":"https:\/\/climatescience.press\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=360040"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/climatescience.press\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=360040"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/climatescience.press\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=360040"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}