{"rewrite":{"id":"r_5ebb06b5acfeee46ed6db06d","clusterId":"c_c78d1009b7b2e042cafe6298","slug":"amd-and-oak-ridge-lab-build-orbit-2-a-0-9-km-weather-ai-model","model":"deepseek-v4-flash","headline":"AMD and Oak Ridge Lab Build ORBIT-2, a 0.9 Km Weather AI Model","summary":"AMD and Oak Ridge National Laboratory developed ORBIT-2, an AI foundation model for global weather downscaling at 0.9 km resolution. The model combines Vision Transformer architecture with scalable algorithms, aims to replace traditional simulation-based forecasting, and is a finalist for the Gordon Bell Prize and a Best Paper Award at Supercomputing 2025.","whyItMatters":"ORBIT-2 moves weather forecasting from simulation-based methods to AI-based methods at an unprecedented global resolution, with enough speed for edge-device deployment and recognition from the HPC community's top awards.","webCardHtml":"\u003cp\u003eAMD and Oak Ridge National Laboratory have released ORBIT-2, an AI foundation model that performs global weather downscaling at 0.9 km resolution. The model uses a Vision Transformer image recognition architecture and scalable algorithms to generate physically consistent predictions of temperature and precipitation. AMD says ORBIT-2 generalizes across regions and variables, shifting weather forecasting from traditional simulation-based approaches to AI-based ones. The model has been selected as a finalist for the Gordon Bell Prize, often called the Nobel Prize of Supercomputing, and for the Best Paper Award at Supercomputing 2025.\u003c/p\u003e\u003cp\u003eAMD highlights three advantages: disaster preparedness through detailed spatial data, infrastructure planning for flood- and heatwave-prone areas, and near-real-time situational awareness. ORBIT-2 can run on edge devices with inference times in milliseconds, broadening access to high-resolution weather data for researchers, policymakers, and industries. Ralph Wittig, Corporate Fellow at AMD, said the project embodies the transformative potential of exascale AI for science.\u003c/p\u003e","blueskyPost":"AMD and Oak Ridge National Lab built ORBIT-2, an AI model that downscales global weather to 0.9 km resolution. It runs on edge devices in milliseconds and is a finalist for the Gordon Bell Prize.","twitterPost":"AMD and Oak Ridge National Lab built ORBIT-2, an AI foundation model for global weather downscaling at 0.9 km resolution. It runs on edge devices in milliseconds and is a finalist for the Gordon Bell Prize.","threadsPost":null,"newsletterBlurb":"AMD and Oak Ridge National Laboratory developed ORBIT-2, an AI foundation model that performs global weather downscaling at 0.9 km resolution. The model is a finalist for the Gordon Bell Prize and the Best Paper Award at Supercomputing 2025, and can run on edge devices with millisecond inference times.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260610-amd-weather-forecasts-ai-orbit-2/\",\"title\":\"AMD Develops 'ORBIT-2,' a Weather Forecasting AI Foundation Model, in Collaboration with Oak Ridge National Laboratory\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4098,"outputTokens":644,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1781062653,"createdAt":"2026-06-10T03:26:36.000Z","publishedAt":"2026-06-10T03:30:33.000Z","updatedAt":"2026-06-10T03:30:33.000Z"},"cluster":{"id":"c_c78d1009b7b2e042cafe6298","canonicalTitle":"AMDがオークリッジ国立研究所と共同で気象予測AI基盤モデルの「ORBIT-2」を開発","representativeArticleId":"a_7096e9fd9e7da58154c13bcb","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-06-10T02:41:00.000Z","lastSeenAt":"2026-06-10T02:41:00.000Z","updatedAt":"2026-06-10T03:30:33.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260610-amd-weather-forecasts-ai-orbit-2/","title":"AMDがオークリッジ国立研究所と共同で気象予測AI基盤モデルの「ORBIT-2」を開発"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":["AMD and Oak Ridge National Laboratory developed ORBIT-2, an AI foundation model for global weather downscaling at 0.9 km resolution.","ORBIT-2 uses a Vision Transformer architecture and scalable algorithms to generate physically consistent predictions of temperature and precipitation.","The model is a finalist for the Gordon Bell Prize and the Best Paper Award at Supercomputing 2025.","ORBIT-2 can run on edge devices with inference times in milliseconds, enabling near-real-time situational awareness.","AMD says ORBIT-2 generalizes across regions and variables, shifting weather forecasting from simulation-based to AI-based methods."]}