arXiv cs.AI· Sasankh Munukutla, Felipe Oviedo, Danrong Zhang, Kenji Takeda, Juan M Lavista Ferres·· 13 小时前AI 评分34
从天气到增强风化：天气基础模型如何用于运营规模的二氧化碳去除
From Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational Scale
AI 导读
研究评估了五个天气基础模型（FM）作为冻结编码器加轻量解码器，在巴西和美国 264 块田地的 5,192 条时间序列上做留一田地验证，用于增强岩石风化（ERW）的碳去除量化。
正文 · 原文
Abstract:Enhanced Rock Weathering (ERW) is a carbon removal solution with the potential to remove gigatons of CO$_2$ per year, but quantifying that removal today requires dense soil sampling and laboratory analysis. We evaluate five weather Foundation Models (FMs) as frozen encoders feeding lightweight decoders, under a leave-one-field-out protocol on 5,192 chronosequences from 264 fields across Brazil and the US. To our knowledge, this is the first holistic evaluation of weather FMs for ERW and the largest evaluation on operational ERW data. We find that across weather FMs, representations transfer to ERW: our best model, TerraNova-ERW, built on Aurora 1.5, positively orders measurements within fields it has never seen. Zero-shot prediction of a new field's mean removal is not yet feasible, and we attribute this to data scale: the same architecture excels on $\sim$$10^5$ natural-weathering sequences, anchoring the scale we expect ERW data must reach. Few-shot prediction, blending the model with a few samples per field, is supported today: TerraNova-ERW recovers over 60% of the highest-removal fields with two samples per field, roughly halves the samples needed to estimate a field's mean removal, and can cut sampling on our densest fields by 28-98%.
| Comments: | Accepted at 40th Conference on Neural Information Processing Systems (NeurIPS 2026), Sydney, Australia. Workshop: Tackling Climate Change with Machine Learning |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28973 [cs.LG] |
| (or arXiv:2610.28973v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28973 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sasankh Munukutla [view email]
[v1]
Tue, 20 Oct 2026 22:47:12 UTC (238 KB)
来源：arXiv cs.AI · arxiv.org