![\"ThousandWorlds:](\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2026\/06\/ThousandWorlds.png\")
<\/p>\n <\/p>\n
\n Dataset overview. Output fields are defined on a 32 \u00d7 64 latitude\u2013longitude grid. There are 53 fields in total and \u223c 105 output dimensions. \u2014 astro-ph.EP <\/p>\n
The search for life beyond Earth will depend on detecting faint signatures in the atmospheres of potentially habitable exoplanets.<\/p>\n
Interpreting those signatures requires understanding the host planet\u2019s climate: the same molecule may signal life on one planet and abiotic chemistry on another. Global climate models (GCMs) provide this understanding, but individual runs can require up to millions of core-hours and substantial domain expert time. Machine-learning emulators could remove this bottleneck, but progress has been limited by the absence of a curated, multi-model exoclimate dataset.<\/p>\n
We introduce ThousandWorlds, an ML-ready benchmark for exoclimate emulation and for the broader regime of low-data, multi-simulator, parameter-to-field regression. The dataset contains approximately 1800 simulations from five GCMs, mapping eight planet parameters to 3D atmospheric fields including temperature, humidity, winds, clouds, and radiation.<\/p>\n
Three nested subsets define progressively harder challenges: single-simulator regression, multi-simulator regression with complete observations, and multi-simulator regression with structured missingness.<\/p>\n
We propose two evaluation protocols: one for ranking methods, and one that measures performance relative to the disagreement between GCMs themselves. We evaluate seven baselines spanning simple methods, deep learning, and Gaussian processes. GP-based methods perform best, suggesting that ThousandWorlds exposes a regime where off-the-shelf deep learning does not yet succeed.<\/p>\n
Edward T. Stevenson, Mei Ting Mak, Eric Wolf, Denis E. Sergeev, Tobi Hammond, N. J. Mayne, Miles Cranmer<\/p>\n
Comments: 10 pages main text, 26 pages references\/appendix, plus NeurIPS checklist. Data: https:\/\/doi.org\/10.57967\/hf\/8695<\/a>. Code: https:\/\/github.com\/edstevenson\/ThousandWorlds<\/a>. Astrobiology, Astrochemistry,<\/p>\n","protected":false},"excerpt":{"rendered":"Dataset overview. Output fields are defined on a 32 \u00d7 64 latitude\u2013longitude grid. There are 53 fields in…\n","protected":false},"author":2,"featured_media":509183,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[145160,10803,910,117170,153800,49380,217477,61,60,82,217478],"class_list":["post-509182","post","type-post","status-publish","format-standard","has-post-thumbnail","category-science","tag-astro-ph-ep","tag-atmosphere","tag-exoplanet","tag-gaia","tag-global-climate-models","tag-habitability","tag-https-astrobiology-com-2026-06-climate","tag-ie","tag-ireland","tag-science","tag-thousandworlds"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/509182","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=509182"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/509182\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/509183"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=509182"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=509182"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=509182"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
Subjects: Machine Learning (cs.LG); Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM)
Cite as: arXiv:2606.18338 [cs.LG] (or arXiv:2606.18338v1 [cs.LG] for this version)
https:\/\/doi.org\/10.48550\/arXiv.2606.18338<\/a>
Focus to learn more
Submission history
From: Edward Stevenson
[v1] Tue, 16 Jun 2026 18:00:00 UTC (5,427 KB)
https:\/\/arxiv.org\/abs\/2606.18338<\/a><\/p>\n