Stochastic Deep Learning Surrogate Models for Uncertainty Propagation in Microstructure-Properties of Ceramic Aerogels

Deep learning surrogate models have become pivotal in enabling model-driven materials discovery to achieve exceptional properties. However, ensuring the accuracy and reliability of predictions from these models, trained on limited and sparse material datasets remains a significant challenge. This study introduces an integrated deep learning framework for predicting the synthesis, microstructure, and mechanical properties of ceramic aerogels, leveraging physics-based models such as Lattice Boltzmann simulations for microstructure formation and stochastic finite element methods for mechanical property calculations. To address the computational demands of repeated physics-based simulations required for experimental calibration and material design, a linked surrogate model is developed, leveraging Convolutional Neural Networks (CNNs) for stochastic microstructure generation and microstructure-to-mechanical property mapping. To overcome challenges associated with limited training datasets from expensive physical modeling, CNN training is formulated within a Bayesian inference framework, enabling robust uncertainty quantification in predictions. Numerical results highlight the strengths and limitations of the linked surrogate framework, demonstrating its effectiveness in predicting properties of aerogels with pore sizes and morphologies similar to the training data (in-distribution) and its ability to interpolate to new microstructural features between training data (out-of-distribution).