用贝叶斯主动学习减少降阶模型训练成本，更高效地预测复杂系统动态。
Cost-effective Reduced-Order Modeling via Bayesian Active Learning
- 基于不确定性感知的贝叶斯POD方法，主动挑选最有信息量的数据点。
- 在杆体温度演化预测中，比其他方法减少计算成本并提升精度。
- 适用于高分辨率数据外推，适合追求高效建模的工程仿真场景。
机器学习代理模型已被用于加速复杂科学与工程问题中的系统动力学求解。为准确捕捉系统动态，现有方法依赖大规模训练数据集，限制了其在实际问题中的应用。本文提出基于不确定性感知贝叶斯本征正交分解（BayPOD-AL）的主动学习框架，旨在从高保真全阶模型中高效学习降阶模型。在预测杆体温度演化的实验中，该方法能有效识别信息量大的数据，显著降低构建训练数据集的计算成本，优于其他不确定性引导的主动学习策略。此外，通过在高于训练数据时间分辨率的测试数据上评估，验证了其泛化能力与效率。
原文摘要 · Abstract (English)
Machine Learning surrogates have been developed to accelerate solving systems dynamics of complex processes in different science and engineering applications. To faithfully capture governing systems dynamics, these methods rely on large training datasets, hence restricting their applicability in real-world problems. In this work, we propose BayPOD-AL, an active learning framework based on an uncertainty-aware Bayesian proper orthogonal decomposition (POD) approach, which aims to effectively learn reduced-order models from high-fidelity full-order models representing complex systems. Experimental results on predicting the temperature evolution over a rod demonstrate BayPOD-AL's effectiveness in suggesting the informative data and reducing computational cost related to constructing a training dataset compared to other uncertainty-guided active learning strategies. Furthermore, we demonstrate BayPOD-AL's generalizability and efficiency by evaluating its performance on a dataset of higher temporal resolution than the training dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。