{"schema":"postcutoff/event@1","as_of":"2026-10-12T07:22:00+02:00","url":"https://postcutoff.com/e/2026-10-09-ai-weather-models-gray-swan-dubai-2024/","md":"https://postcutoff.com/e/2026-10-09-ai-weather-models-gray-swan-dubai-2024/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-09-ai-weather-models-gray-swan-dubai-2024","date":"2026-10-09","date_precision":"day","short_title":"AI weather models forecast Dubai's unprecedented 2024 storm by 'translocation', not extrapolation (University of Chicago, Science Advances)","deck":null,"takeaway":"GraphCast and AIFS forecast it accurately up to 8 days ahead; FuXi underestimated the rain.","category":"science","category_label":"Science & math","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"Science Advances: Predicting regional gray swans via translocation","url":"https://www.science.org/doi/10.1126/sciadv.ady9406","type":"paper","group":"primary","domain":"science.org"}],"official":1,"filed":"2026-10-12","updated":"2026-10-12","orgs":["University of Chicago"],"title":"AI weather models forecast Dubai's unprecedented 2024 storm by 'translocation', not extrapolation (University of Chicago, Science Advances)","summary":"A Science Advances paper (vol. 12, issue 41, published 9 Oct 2026) by Y. Qiang Sun, Pedram Hassanzadeh and colleagues tested GraphCast, AIFS and FuXi on the April 2024 Dubai storm, which had twice the highest rainfall in the training data for that region. GraphCast and AIFS forecast it accurately up to 8 days ahead; FuXi underestimated the rain. The authors attribute the success to \"translocation\", learning from similar or stronger events elsewhere on the globe, and find no evidence that the models extrapolate from weaker events. Events in the tail of the global distribution are still forecast poorly.","key_facts":["Paper: 'Predicting regional gray swans via translocation: AI weather models and Dubai's unprecedented 2024 rainfall', Science Advances 12(41), doi 10.1126/sciadv.ady9406; Y. Qiang Sun, Pedram Hassanzadeh, Tiffany Shaw, Hamid A. Pahlavan, Adam Marchakitus (Department of the Geophysical Sciences, University of Chicago)","Abstract: the storm 'had twice the training set's highest rainfall in that region. GraphCast and AIFS accurately forecast this event up to 8 days ahead. FuXi forecasts the event but underestimates the rainfall.'","Mechanism (abstract): fine-tuning and receptive-field analyses 'suggest that these models' success stems from \"translocation\": learning from comparable/stronger dynamically similar events in other regions during training. Evidence of \"extrapolation\" (learning from weaker events) is not found.'","Limit (abstract): 'Even events within the global distribution's tail are poorly forecasted, which is not only due to data imbalance (generalization error) but also spectral bias (optimization error).'","Written from the abstract (Crossref); the full text was not read"],"key_numbers":[],"tags":["climate-weather","weather-forecasting","graphcast","aifs","fuxi","extremes","generalization","peer-reviewed"],"science":{"field":"climate-weather","subfield":"AI weather forecasting / extremes","problem":"Can AI weather models forecast extremes stronger than anything in their regional training data?","result":"Yes for a regionally unprecedented event (Dubai 2024), by transferring from similar events elsewhere; no evidence of extrapolation beyond the global training distribution.","open_since":"","ai_system":["GraphCast","AIFS","FuXi"],"human_role":"Human-led evaluation study of existing AI models","verification":{"key":"peer-review","label":"Peer-reviewed","text":"Peer-reviewed in Science Advances"},"status":"confirmed","shock":"","short":"AI weather models and regional gray swans"},"body_md":"## What happened\n\nA common worry about data-driven weather models is that they cannot predict events more extreme than those they were trained on\n(\"gray swans\"). The Chicago group examined a real case: the 2024 Dubai rainfall, far beyond the regional record in the training\nset. Two of three leading models forecast it well more than a week ahead. The analysis indicates that the models reused what they\nhad learned from comparable storms in other parts of the world.\n\n## Why it matters\n\nIt separates two kinds of extremes. Regionally unprecedented events can be forecast if something similar happened elsewhere.\nGlobally unprecedented ones remain a weakness, and the paper traces part of it to how the networks are optimized, which suggests\nwhere to improve them.","disputed":[],"related":[{"id":"2026-08-06-weathernext-open-source","url":"https://postcutoff.com/e/2026-08-06-weathernext-open-source/","date":"2026-08-06","date_precision":"day","short_title":"DeepMind open-sources WeatherNext 2 and WeatherNext Cyclones with a Nature paper showing ~1 extra day of hurricane warning","deck":null,"takeaway":null,"category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":10,"official":4,"filed":"2026-09-29","updated":"2026-10-11","orgs":["Google DeepMind","Google Research"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-12","type":"filed","text":"Created from the Science Advances table of contents and the Crossref abstract"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-12","run":null,"sources_read":"The Science Advances table of contents and the Crossref abstract","updated":"2026-10-12","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":162,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":101,"in_training_data":false},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":192,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":131,"in_training_data":false}],"short_url":null}