arXiv cs.AI· Zhi-Song Liu, Wenqing Peng, Ammar Kheder, Michael Boy·· 12 小时前AI 评分34
FNO-MoE：可单次预测30分钟近显式大气化学状态的神经算子
An actively trained neural operator for near-explicit atmospheric chemistry
AI 导读
FNO-MoE 是一种结合专家混合的傅里叶神经算子，可在单次调用中预测未来30分钟的完整近显式化学状态，覆盖数千种物种。该网络利用专家间分歧主动挑选最具信息量的箱模型模拟来指导自身训练，同等成本下精度优于随机或均匀采样。经长轨迹微调后，它可在多小时运行中保持稳定，对未见化学组分仍准确，速度比数值求解器快数个数量级。
正文
Abstract:Earth-system models simplify atmospheric chemistry into condensed mechanisms, because near-explicit mechanisms such as the Master Chemical Mechanism (MCM) are too costly to solve in every grid cell. Neural emulators could lift this limit, but most advance the chemistry in small time steps and cover only a few species or a reduced mechanism. Here we introduce FNO-MoE, a Fourier neural operator with a mixture of experts that predicts the full near-explicit chemical state over 30 minutes in a single call. The same network also guides its own training, using the disagreement among its experts to select the most informative box-model simulations. At equal cost, this active sampling yields a more accurate emulator than random or evenly spread sampling. Fine-tuning on longer trajectories keeps it stable over multi-hour runs in which models trained on short simulations diverge. The resulting emulator reproduces the evolution of thousands of species with high fidelity, remains accurate for unseen chemical compositions and runs orders of magnitude faster than the numerical solver. These results open a new direction for emulating complex atmospheric systems: neural operators that predict the full chemical state over long windows and choose their own training data. Training under changing meteorology is the next step towards bringing near-explicit chemistry into Earth-system models.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.33771 [cs.AI] |
| (or arXiv:2610.33771v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33771 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenqing Peng [view email]
[v1]
Sat, 24 Oct 2026 16:22:33 UTC (9,561 KB)
来源：arXiv cs.AI · arxiv.org