{"id":26310,"date":"2026-01-05T11:51:02","date_gmt":"2026-01-05T16:51:02","guid":{"rendered":"https:\/\/www.realclimate.org\/?p=26310"},"modified":"2026-01-05T11:51:06","modified_gmt":"2026-01-05T16:51:06","slug":"ai-ml-climate-magic","status":"publish","type":"post","link":"https:\/\/www.realclimate.org\/index.php\/archives\/2026\/01\/ai-ml-climate-magic\/","title":{"rendered":"AI\/ML climate magic?"},"content":{"rendered":"
\n\n

There has been a frenzy around artificial intelligence and deep machine learning (AI\/ML) since the \u201cChatGPT Moment\u201d in 2022, and AI\/ML is for sure going to affect us all. It strikes me that this buzz also looks more like a science fiction story<\/a> (utopy\/dystopy) than the old-fashion Clondyke goldrush craze. <\/p>\n\n\n\n\n\n\n\n

\u201cAI will not replace you. A person using AI will replace you<\/a>\u201d we have been told, and people from high places have made it clear that we need to adopt AI\/ML. I certainly feel the pressure from those who want to promote more AI\/ML in downscaling global climate models, but they don\u2019t seem to know the history of downscaling climate projections. <\/p>\n\n\n\n

Nevertheless, I can understand this urge and desire, because it is not just due to large language models (LLMs<\/a>) such as chatGPT. A more relevant motivation is more likely the impressive successes in applying AI\/ML to weather forecasting (Bi et al., 2023)<\/a><\/span>, such as Pangu-Weather<\/a>, GraphCast<\/a>, AIFS<\/a>,Earth-2<\/a>, and Aurora<\/a>.<\/p>\n\n\n\n

Yet there is a subtle, and profound, difference between downscaling climate model results for weather forecasting and climate change, and I have written a few words of caution in a paper<\/a> recently posted on arXiv.<\/p>\n\n\n\n

I fear that more statistics and mathematics based methods are being ditched, and a metaphor for this is the cuckoo laying eggs in other birds nests. We have developed methods for downscaling salient climate information based on mathematics and statistics, which I believe will give more accurate results than present AI\/ML algorithms and strategies. <\/p>\n\n\n\n

I think it\u2019s important not to forget that the recent success of AI\/ML does not diminish the standing of mathematics, statistics and physics, but AI\/ML is useful when there is a lot of data and incomplete knowledge concerning how things interact. However, the quality of data, what it really represents, and its volume has a big impact on the simulations.   <\/p>\n\n\n\n

There are some concerns that AI\/ML give inaccurate results, such as in Google summaries<\/a>, it being a \u201cblack box\u201d and that it may \u201challlucinate\u201d. When it comes to downscaling climate change, the biggest problem is perhaps that AI\/ML algorithms are trained on data that are not representative in a future warmer climate.<\/p>\n\n\n\n

AI\/ML should complement more traditional methods, because they are based on different assumptions and have different strengths and weaknesses, but I fear it may replace them because short-term-thinking accountants and administrators want to cut costs.\u00a0
Other concerns are the carbon foot-print from data centres<\/a> needed for AI\/ML and how it facilitates dogmatic thinking<\/a>, in addition to the risk that careless or inappropriate use of AI\/ML may lead to maladaptation. More details and references are provided in the arXiv paper Benestad (2026)<\/a>.<\/p>\n

References<\/h2>\n
    \n
  1. <\/a>\nK. Bi, L. Xie, H. Zhang, X. Chen, X. Gu, and Q. Tian, \"Accurate medium-range global weather forecasting with 3D neural networks\", Nature<\/i>, vol. 619, pp. 533-538, 2023. http:\/\/dx.doi.org\/10.1038\/s41586-023-06185-3<\/a>\n\n\n<\/li>\n<\/ol>\n\n<\/div> ","protected":false},"excerpt":{"rendered":"

    There has been a frenzy around artificial intelligence and deep machine learning (AI\/ML) since the \u201cChatGPT Moment\u201d in 2022, and AI\/ML is for sure going to affect us all. It strikes me that this buzz also looks more like a science fiction story (utopy\/dystopy) than the old-fashion Clondyke goldrush craze. <\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"_genesis_hide_title":false,"_genesis_hide_breadcrumbs":false,"_genesis_hide_singular_image":false,"_genesis_hide_footer_widgets":false,"_genesis_custom_body_class":"","_genesis_custom_post_class":"","_genesis_layout":"","footnotes":""},"categories":[5,1,48,75,38],"tags":[],"class_list":["post-26310","post","type-post","status-publish","format-standard","category-climate-modelling","category-climate-science","category-downscaling","category-featured-story","category-scientific-practice","entry"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t