iFLEX：面向科学机器学习时间插值的生成式残差修正学习方法
Generative Refinement Learning for Temporal Interpolation in Scientific Machine Learning
AI 导读
研究者提出 iFLEX 模型，用条件扩散模型学习修正加权平均插值的残差，以重建科学场数据中缺失的中间时刻场。模型以两次观测、目标时间、观测间隔和物理参数为条件，在 Navier-Stokes Kraichnan 湍流、上海雷达降水和海表温度数据集上重建误差均低于光学流和视频帧插值扩散模型等基线。
正文 · 原文
Abstract:Computationally expensive simulations and real-world observations often provide data at a lower temporal resolution than downstream tasks require. Averaging observations at fixed grid points can introduce errors, and motion estimates alone do not determine how the physical field values change. In this work, we study whether learning to correct a simple numerical interpolation improves the reconstruction of intermediate scientific fields. Our model, interpolative FLow EXpert (iFLEX), first estimates the missing field by taking a weighted average of the two observations at each grid point, giving more weight to the observation closer to the requested time. During training, subtracting this estimate from an observed intermediate field gives the residual that a conditional diffusion model learns to generate. Both observations condition the model, together with the target time, the interval between observations, and available physical parameters. To reconstruct an unobserved intermediate field, the generated residual is added to the weighted average. We evaluate iFLEX on Navier-Stokes Kraichnan turbulence, Shanghai radar precipitation, and sea surface temperature. Across these datasets, iFLEX achieves lower reconstruction error than the evaluated baselines, including optical-flow and diffusion models developed for video frame interpolation in computer vision. In a controlled turbulence comparison at a Reynolds number of 36,000, learning the residual reduces relative Frobenius norm error from about 13.7 for direct field generation to 10.5, with the diffusion backbone and training setup held fixed. Code is available at this https URL.
| Comments: | Accepted by Transactions on Machine Learning Research |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Mathematical Physics (math-ph); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.36751 [cs.LG] |
| (or arXiv:2610.36751v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36751 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pu Ren [view email]
[v1]
Tue, 27 Oct 2026 07:08:23 UTC (4,874 KB)
来源：arXiv cs.AI · arxiv.org