Skip to content
Original
ResearchHugging Face BlogFrom the source·· 2 days agoPicks

HiRO-ACEv2 simulates extreme weather at 3 km resolution for a fraction of the cost

HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

Who
AllenAI
What
introduces HiRO-ACEv2, an AI system for generating global 3 km climate data
Quote
We introduce HiRO-ACEv2 , the newest update to our High Resolution Output Ai2 Climate Emulator (HiRO-ACE) system.

What happened

Ai2 introduced HiRO-ACEv2, an updated climate emulator that generates global 3 km rain, wind, and pressure data at about 1/300th the cost of X-SHiELD. Given coarsened X-SHiELD data, its HiROv2 downscaling model matches high-resolution statistics to within 3%, even for events occurring once in a million data points. The system currently works only with ACE tuned to match X-SHiELD and cannot yet generate high-resolution data for other climates; downloadable models, tutorial notebooks, and a web demo are available.

Why it matters

The comparison with X-SHiELD gives researchers a concrete cost and accuracy reference for extreme weather simulations, with applicability currently limited to the climate represented in training.

The story so far

Ai2 introduced HiRO-ACEv2, an updated climate emulator that it says generates global rain, wind, and pressure data at 3 km resolution for about 1/300th the cost of X-SHiELD; downloadable models, tutorial notebooks, and a web demo are available. Given coarsened data from X-SHiELD, Ai2 says the system’s HiROv2 downscaling model reproduces high-resolution statistics to within 3%, including for extreme events occurring once in a million data points. Its scope remains tied to that training simulation: HiRO works only with the version of ACE tuned to match X-SHiELD and cannot yet generate high-resolution data for other climates. The web demo shows pre-generated precipitation, wind, and sea-level pressure outputs from HiROv1 and HiROv2 alongside X-SHiELD output.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline

Trending now

  1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
  2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
  3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
  4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights

Tomorrow at 08:00, a briefing like this arrives in your inbox.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-17