Joint Parameter and Parameterization Inference with Uncertainty Quantification through Differentiable Programming
Accurate representations of unknown and sub-grid physical processes through parameterizations (or closure) in numerical simulations with quantified uncertainty are critical for resolving the coarse-grained partial differential equations that govern many problems ranging from weather and climate prediction to turbulence simulations. Recent advances have seen machine learning (ML) increasingly applied to model these subgrid processes, resulting in the development of hybrid physics-ML models through the integration with numerical solvers. In this work, we introduce a novel framework for the joint estimation of physical parameters and machine learning parameterizations with uncertainty quantification. Our framework incorporates online training and efficient Bayesian inference within a high-dimensional parameter space, facilitated by differentiable programming. This proof of concept underscores the substantial potential of differentiable programming in synergistically combining machine learning with differential equations, thereby enhancing the capabilities of hybrid physics-ML modeling.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceUncertainty QuantificationSimilar Papers 제목 키워드 기반
Parameter Estimation and Uncertainty Quantification for Systems Biology Models
Mathematical models can provide quantitative insight into immunoreceptor signaling, but require parameterization and uncertainty quantification before making reliable predictions. We review currently available methods an…
Bayesian Inferenceparameter estimationUncertainty QuantificationGenerative Parameter Sampler For Scalable Uncertainty Quantification
Uncertainty quantification has been a core of the statistical machine learning, but its computational bottleneck has been a serious challenge for both Bayesians and frequentists. We propose a model-based framework in qua…
General ClassificationUncertainty QuantificationStochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal da…
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models. However, it remains unclear how to tune the…
Bayesian InferenceMultivariate Probabilistic Time Series Forecasting with Correlated Errors
Accurately modeling the correlation structure of errors is critical for reliable uncertainty quantification in probabilistic time series forecasting. While recent deep learning models for multivariate time series have de…
Computational EfficiencyProbabilistic Time Series ForecastingTime SeriesTime Series Forecasting+1