Physics-informed machine learning (PIML) integrates prior physical information, often in the form of differential equation constraints, into the process of fitting machine learning models to physical data. Popular PIML approaches, including neural operators, physics-informed neural networks, neural ordinary differential equations, and neural discrete equilibria, are typically fit to objectives that simultaneously include both data and physical constraints. However, the multi-objective nature of this approach creates ambiguity in the measurement of model quality. This is related to a poor understanding of epistemic uncertainty, and it can lead to surprising failure modes, even when existing statistical metrics suggest strong fits. Working within a Gaussian process regression framework, we introduce the Physics-Informed Log Evidence (PILE) score. Bypassing the ambiguities of test losses, the PILE score is a single, uncertainty-aware metric that provides a selection principle for hyperparameters of a PIML model. We show that PILE minimization yields excellent choices for a wide variety of model parameters, including kernel bandwidth, least squares regularization weights, and even kernel function selection. We also show that, even prior to data acquisition, a special 'data-free' case of the PILE score identifies a priori kernel choices that are 'well-adapted' to a given PDE. Beyond the kernel setting, we anticipate that the PILE score can be extended to PIML at large, and we outline approaches to do so.
Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
Departamento de Ciencia de la Computación, Pontificia Universidad Católica de Chile(计算机科学系,天主教智利大学);Department of Computer Science, University of Tübingen(计算机科学系,图宾根大学);John A. Paulson School of Engineering and Applied Sciences, Harvard University(工程与应用科学学院,哈佛大学)
Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics
Department of Electronics and Computer Science(电子与计算机科学系);Mondragon University(蒙得龙大学);Research & Development(研发);CARTIF Technology Centre(CARTIF技术中心);Department of Physical Chemistry(物理化学系);University of the Basque Country (EHU)(巴斯克国家大学(EHU));Basque Centre for Applied Mathematics (BCAM)(巴斯克应用数学中心(BCAM));Department of Computer Science and Artificial Intelligence(计算机科学与人工智能系)
Uncertainty-Aware Prediction of Lung Tumor Growth from Sparse Longitudinal CT Data via Bayesian Physics-Informed Neural Networks
Department of Mathematics, Vanderbilt University(范德比大学数学系);John A. Paulson School of Engineering and Applied Science, Harvard University(哈佛大学约翰·A·保罗森工程与应用科学学院)
PUNCH: Physics-informed Uncertainty-aware Network for Coronary Hemodynamics
AngioInsight Inc.(AngioInsight公司);University of California, Los Angeles(加州大学洛杉矶分校);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Michigan(密歇根大学);Cardiovascular Research Foundation(心血管研究基金会);University of California, Riverside(加州大学河滨分校)
UBMF: Uncertainty-Aware Bayesian Meta-Learning Framework for Fault Diagnosis with Imbalanced Industrial Data
Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院);Institute of Reliability Engineering, Beihang University(北京航空航天大学可靠性工程研究所);Science & Technology on Reliability & Environmental Engineering Laboratory(可靠性与环境工程技术重点实验室);School of Reliability and Systems Engineering, Beihang University(北京航空航天大学可靠性与系统工程学院)
Prediction of wind turbines power with physics-informed neural networks and evidential uncertainty quantification
University of Granada(格拉纳达大学);Research Centre for Information and Communication Technologies (CITIC-UGR)(信息与通信技术研究中心(CITIC-UGR));TECNALIA(泰克纳利亚研究中心);Imperial College London(帝国理工学院)
Variational Quantum Physics-Informed Neural Networks for Hydrological PDE-Constrained Learning with Inherent Uncertainty Quantification
Faculty of Computer Science and Multimedia, Lincoln University College, Petaling Jaya, Selangor, Malaysia(计算机科学与多媒体学院,林肯大学学院,Petaling Jaya,Selangor,马来西亚)
Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification
Environmental Geosciences, Department of Geosciences, University of Oslo(奥斯陆大学环境地质学系);National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)(中国石油大学(北京)石油资源与工程国家级重点实验室);College of Geosciences, China University of Petroleum (Beijing)(中国石油大学(北京)地质学院);State Key Laboratory of Coal Mine Disaster Prevention and Control, China University of Mining and Technology(中国矿业大学煤矿灾害防治控制国家重点实验室);The Lyell Centre, Heriot-Watt University(赫瑞斯泰大学利尔中心);Subsurface Energy Transition and Innovation Centre, Heriot-Watt University(赫瑞斯泰大学地下能源转型与创新中心)
Uncertainty quantification for noisy inputs-outputs in physics-informed neural networks and neural operators
Brown University(布朗大学);Huazhong University of Science and Technology(华中科技大学);Institute of Interdisciplinary Research for Mathematics and Applied Science, School of Mathematics and Statistics, Huazhong University of Science and Technology(华中科技大学数学与统计学院数学与应用科学交叉研究院)
Gryphon Center for Artificial Intelligence and Theoretical Sciences(格里芬人工智能与理论科学中心);Georgia Institute of Technology(佐治亚理工学院);University of Pennsylvania(宾夕法尼亚大学)
NeuroPhysNet: A FitzHugh-Nagumo-Based Physics-Informed Neural Network Framework for Electroencephalograph (EEG) Analysis and Motor Imagery Classification
University of Technology Sydney(新南威尔士大学悉尼分校);Queensland University of Technology(昆士兰理工大学)
Within-fire estimates of biomass loss across national forests of the US West Coast: inventory-informed inference with uncertainty
Michigan State University(密歇根州立大学);South Dakota School of Mines & Technology(南达科他矿业理工学院);USDA Forest Service, Pacific Northwest Research Station(美国农业部林务局,太平洋西北研究站);Northern Research Station, United States Department of Agriculture Forest Service(美国农业部林务局北方研究站);USDA Forest Service, Rocky Mountain Research Station(美国农业部林务局,落基山研究站)
Nonlinearity and Uncertainty Informed Moment-Matching Gaussian Mixture Splitting
Department of Mechanical and Aerospace Engineering, Utah State University(机械与航空航天工程系,犹他州立大学);School of Aeronautics and Astronautics, Purdue University(航空航天工程学院,普渡大学)
Multi-level informed optimization via decomposed Kriging for large design problems under uncertainty
Reliability and Risk Engineering Laboratory, Institute of Energy and Process Engineering, Department of Mechanical and Process Engineering, ETH Zurich(可靠性与风险工程实验室,能源与过程工程研究所,机械与过程工程系,苏黎世联邦理工学院)
Physics-informed random neural architectures on compact boundaryless multiply connected manifolds for random-operator models in machine learning and uncertainty quantification