--- title: The forecast is better than ever. The physics is not. description: Google DeepMind outperformed the National Hurricane Center on storm track this season. A storm-resolving AI runs 50 times more efficiently than the physics model. And a new framework exists because the models hallucinate physics. canonical: https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/ last-updated: 2026-11-13 url: https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/ published: 2026-11-13T12:43:37Z edition: 2026-11-13T12 newsroom: artificial-intelligence beat: research trust: reported source_count: 3 cited_manifest_ids: ['1794515844353872357', '1794559347298136585', '1794559347298136583'] --- # The forecast is better than ever. The physics is not. *Google DeepMind outperformed the National Hurricane Center on storm track this season. A storm-resolving AI runs 50 times more efficiently than the physics model. And a new framework exists because the models hallucinate physics.* Reported · 3 Manifests · Artificial Intelligence · Published 2026-11-13 12:43 UTC ## Key facts - Brightband reports Google DeepMind outperformed operational GFS, HAFS-A, HAFS-B and NHC forecasts in track forecast errors for the 2026 East Pacific hurricane season, with the highest frequency of superior performance, and is now consistently used in the Hurricane Center forecast process. (self-reported) [cites: 1794515844353872357] - Brightband reports Google DeepMind exhibited a consistent negative intensity bias in the 2026 East Pacific season. (self-reported) [cites: 1794515844353872357] - In a preprint, the STRATA model achieves 48 simulated days per MWh, a 50x energy efficiency gain over the SCREAM physics model, and 741 simulated days per wall-clock day on 512 H100 GPUs. (self-reported) [cites: 1794559347298136585] - In a preprint, the PhysXAI framework decouples forecast error from physical plausibility and supports detection and attribution across GraphCast, Pangu-Weather and NeuralGCM. (self-reported) [cites: 1794559347298136583] ## The forecast wins The 2026 hurricane season is the one where the AI forecast stopped being an experiment. Brightband's analysis of Google DeepMind's performance finds it outperformed operational GFS, HAFS-A, HAFS-B and National Hurricane Center forecasts in track forecast errors for the East Pacific season, with the highest frequency of superior performance for track forecasts. Performance in the Atlantic was similarly strong, with DeepMind the best-performing model for track forecasts at most lead times. The institutional seal is the last line of the analysis: Google DeepMind is now consistently used in the Hurricane Center forecast process. The AI model is no longer competing with the forecasters. It is part of how they forecast. [cites: 1794515844353872357] The same analysis carries the caveat that keeps the story honest. Despite its overall accuracy, Google DeepMind displayed a consistent negative intensity bias in the East Pacific season — it underestimates how strong the storm will be. Atlantic conclusions are limited by the season's low activity and smaller sample size. The model is better at where the storm goes than at how strong it will be when it gets there. For anyone whose decisions depend on intensity — evacuation orders, insurance, port closures — the track record is not the whole record. [cites: 1794515844353872357] ## The simulation scales The second paper of the week scales the same bargain up to the whole planet. STRATA achieves 48 simulated days per megawatt-hour — a 50 times energy efficiency gain over the SCREAM physics model — and 741 simulated days per wall-clock day on 512 H100 GPUs. Kilometre-scale emulation still requires roughly ten times more floating-point operations per grid point than coarse-resolution AI weather models, and large-scale biases develop in STRATA rollouts with lead time. The simulation is fifty times cheaper to run than the physics, and it drifts as it runs. Both facts are true at once, and the second is the price of the first. [cites: 1794559347298136585] > **From Synorb** — Run the cited Manifests yourself. Every claim in this paper points to a Manifest id. Get a Synorb Key and read the Manifests behind it. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons. [Get a key](https://synorb.com/connect/start) ## The physics check The third paper exists because of that drift. PhysXAI introduces a diagnostic framework to identify what its authors call physical hallucinations: outputs that violate fundamental laws such as mass conservation in modern weather foundation models. The framework decouples forecast error from physical plausibility, so a forecast can be scored on two axes at once — how close it is, and whether it obeys physics. It supports detection and attribution across GraphCast, Pangu-Weather and NeuralGCM, and its latent representation is approximately isometric to the physical residual space, which means the model's internal geometry tracks the physics it is supposed to respect. The point of the tool is not to replace the forecasters. It is to tell them which parts of a good-looking forecast are physically impossible. [cites: 1794559347298136583] Put the three together and the state of AI weather is clear. The forecast is now good enough to sit inside the Hurricane Center's process, the simulation is cheap enough to run at planetary scale, and the field has built the instrument that catches the models breaking the laws of physics. The bargain of AI weather is accuracy without obedience, and the work this week is about closing that gap — measuring the bias, pricing the drift, and mapping the hallucination. The forecast you can trust is the one that has been checked twice: once against the storm, and once against physics. [cites: 1794515844353872357, 1794559347298136583] ## What is still unresolved - Whether the negative intensity bias can be corrected without losing track accuracy - Whether large-scale biases in storm-resolving rollouts can be bounded - Whether physical plausibility diagnostics become standard in operational forecasting ## Decision card - **Useful for:** Professionals who depend on weather forecasts; Operators deciding where AI weather models can be trusted - **Not for:** Treating an AI forecast's accuracy as proof it respects physics; Using storm intensity numbers without checking for bias - **Compare against:** Your own forecast's track error against the operational models; The energy cost of a physics run against an AI emulation ## Provenance ledger | Manifest id | Title | Source | Claims used | Published | |---|---|---|---|---| | `1794515844353872357` | Google DeepMind Performance During the 2026 Hurricane Season: AI Models Discussion 11-12-2026 | [brightband-blog](https://brightband.com/blog/google-deepmind-performance-during-the-2026-hurricane-season-ai-models-discussion-11-12-2026) | 1794516080342872877, 1794516080344872878, 1794516080339872875, 1794516080347872880, 1794516080348872881 | 11-12 00:00 | | `1794559347298136585` | Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet | [arxiv-frontier-methods-select](https://arxiv.org/pdf/2606.31248v2) | 1794559732424138591, 1794559732426138593, 1794559732427138594, 1794559732429138596 | 11-13 00:00 | | `1794559347298136583` | PhysXAI: A Theoretical Framework for Diagnosing Physical Hallucinations in Weather Foundation Models | [arxiv-frontier-methods-select](https://arxiv.org/pdf/2611.15053v1) | 1794559729639138055, 1794559729671138057, 1794559729659138056 | 11-13 00:00 | ## Run these Manifests yourself Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them. 1. **Get a Synorb Key.** Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{"client":"your-agent-name"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons. 2. **Read each cited Manifest by id.** REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer `. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief. 3. **Check the claim.** Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them. Cited Manifest ids: - `1794515844353872357` - `1794559347298136585` - `1794559347298136583` ```sh for id in 1794515844353872357 1794559347298136585 1794559347298136583; do curl -s -H "Authorization: Bearer $SYNORB_KEY" "https://api.synorb.com/manifests/by-id/$id" done ``` > **From Synorb** — Connect your agent over MCP. Add https://mcp.synorb.com/mcp to your agent, then call the tool synorb-get-demo-key if it has no key yet. It needs no email and no form. Keys are free for 72 hours, and new keys are limited per network. [How to connect](https://synorb.com/connect/start) ## Related stories - [Agents just proved a 13-year-old conjecture — and science AI is getting both stronger and more honest](https://hangingcontext.com/stories/2026-11-14/teamwork-agents-solve-open-science-problems/) - [AI is moving into the home and the wallet, with your keys and your face as the boundary](https://hangingcontext.com/stories/2026-11-14/ai-moves-into-home-and-wallet/) - [Legal AI vendors compete on how the work gets built](https://hangingcontext.com/stories/2026-11-13/legal-ai-vendors-build-in-the-field/) - [Healthcare AI stops summarising and starts running the work](https://hangingcontext.com/stories/2026-11-13/healthcare-ai-becomes-workflow/) ## Links - HTML: https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/ - JSON: https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/index.json - Markdown: https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/index.md Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify. --- Reuse (terms v1): Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product. Credit: "Hanging Context, with provenance by Synorb", with a link to https://hangingcontext.com/stories/2026-11-13/weather-ai-wins-forecast-breaks-physics/. Terms: https://hangingcontext.com/terms/reuse/