发表机构
University of British Columbia（不列颠哥伦比亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对油气长期产量预测的不适定问题，提出单调约束扩散模型Physics-SIMS-TS，结合负引导、递减曲线约束、同单调投影和集成采样，在超3.5万口井上达到最准确扩散预测性能，且预测单调性代价极小。
AI 中文摘要
仅从序列的前几个观测值预测长时间范围是不适定问题：许多轨迹与相同的短期历史一致。我们在油气产量预测中研究这一问题，在该场景中，基于一口井生产寿命大约前五分之一所做的预测驱动开发与弃置决策，且可用预测必须描述单调递减趋势。我们提出Physics-SIMS-TS，一种条件扩散预测器，它结合了针对合成伪影的负引导、递减曲线约束、采样时应用的同单调投影、空间训练增强，以及产生完整预测分布的集成随机采样器。在三个管辖区和超过35,000口井上，在共享空间、验证冻结协议下，Physics-SIMS-TS是比较中最准确的扩散预测器，并与集成Transformer预测器具有竞争力，但不优于后者。其预测通过构造保证单调，代价是均方误差最多增加0.5%，其轨迹集成在每辖区拟合一个离散因子后产生校准区间。在六个标准基准上，骨干网络的可逆实例归一化变体是领先的扩散基线。我们还量化了四个影响测量排名的协议选择。代码和评估工件已发布。
英文摘要
Forecasting a long horizon from only the first observations of a sequence is ill-posed: many trajectories are consistent with the same short history. We study this problem in oil and gas production forecasting, where forecasts made after roughly the first fifth of a well's producing life drive development and abandonment decisions, and where a usable forecast must describe a monotone decline. We present Physics-SIMS-TS, a conditional diffusion forecaster that combines negative guidance against synthetic artifacts, decline-curve constraints and an isotonic projection applied during sampling, spatial training augmentation, and an ensembled stochastic sampler yielding a full predictive distribution. Across three jurisdictions and more than 35,000 wells, under a shared-space, validation-frozen protocol, Physics-SIMS-TS is the most accurate diffusion forecaster in the comparison and is competitive with, but not superior to, ensembled transformer forecasters. Its forecasts are monotone by construction at a cost of at most 0.5% in mean squared error, and its trajectory ensemble yields calibrated intervals after one dispersion factor is fitted per jurisdiction. On six standard benchmarks a reversible-instance-normalization variant of the backbone is the leading diffusion baseline. We also quantify four protocol choices on which the measured ranking depends. Code and evaluation artifacts are released.
Comments34 pages, 4 figures. Under review at the Journal of Machine Learning Research. Extended version of a paper at Canadian AI 2026 (PMLR 318, pp. 332-341)
