PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction

TL;DR

PI-JEPA is a novel physics-informed pretraining framework for multiphysics simulations that reduces reliance on labeled data by using masked latent prediction and operator-split regularization.

Contribution

It introduces a label-free pretraining method for neural surrogates that leverages operator-split structure and physics constraints, enabling effective fine-tuning with minimal labeled data.

Findings

Achieves 1.9x lower error than FNO on Darcy flow with 100 labeled runs.

Demonstrates 2.4x lower error than DeepONet at 100 labeled runs.

Reduces simulation budget for multiphysics surrogate deployment.

Abstract

Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation trajectories and cannot exploit this unlabeled structure. We introduce \textbf{PI-JEPA} (Physics-Informed Joint Embedding Predictive Architecture), a surrogate pretraining framework that trains \emph{without any completed PDE solves}, using masked latent prediction on unlabeled parameter fields under per-sub-operator PDE residual regularization. The predictor bank is structurally aligned with the Lie--Trotter operator-splitting decomposition of the governing equations, dedicating a separate physics-constrained latent module to each sub-process (pressure, saturation transport, reaction), enabling fine-tuning with as few as 100 labeled simulation runs. On single-phase Darcy flow, PI-JEPA achieves $1.9\times$ lower error than FNO and $2.4\times$ lower error than DeepONet at $N_\ell{=}100$, with 24\% improvement over supervised-only training at $N_\ell{=}500$, demonstrating that label-free surrogate pretraining substantially reduces the simulation budget required for multiphysics surrogate deployment.