Summary: This work improves computational efficiency in high-dimensional complex model prediction by developing an AI-based inversion-free framework.

Accomplishment: The traditional model prediction workflow, which calibrates models to match observations and then uses the calibrated models for predictions, relies heavily on inverse modeling to constrain uncertain parameters in complex forward models. This inversion-based prediction approach is infeasible for complex models with heterogeneous parameter uncertainties and incapable of rapid integration of streaming and multiple sources of data because of the difficulty and computational cost in the model inversion, which is typically ill-posed and can require hundreds of thousands of expensive forward simulations to be performed iteratively. We propose to circumvent inverse modeling by precomputing an ensemble of unconstrained forward simulations and then using machine learning (ML) methods to learn the statistical relationship between simulated observation and prediction quantities. Once the ML model has learned the relationship, it can be used to make predictions of future system behavior with uncertainty quantification based on observations. The proposed learning-based inversion-free model prediction (LIMP) framework is computationally efficient which only requires a few hundreds or thousands of fully parallelizable forward simulations. Additionally, LIMP can continually update predictions based on streaming observations from multiple locations and sources without necessarily requiring extra model simulations.

Significance and Impact: Many scientific applications are requiring model prediction for advancing the understanding of the system. This work addressed traditional inversion-based model prediction challenges and improved computational efficiency of model prediction in high-dimensional complex problems. The developed LIMP framework is efficient and flexible that can be used for fast model prediction, rapid data assimilation, and cost-effective experimental design. Additionally, the framework transforms a model prediction problem from traditional iterative calculation to a parallel computing which can greatly leverage modern supercomputers.

Reference: https://ieeexplore.ieee.org/document/8955590

Funding: Research of this work is supported by LDRD AI initiative and software development is supported by DOE SciDAC project.