Adaptive Surrogate Models with Unbalanced Data for Material Design

Accurately predicting the materials’ responses, such as strain and energy, under certain loading conditions is crucial for developing fundamental structure-property relationships and facilitating material design. However, this process can be computationally expensive and challenging, especially for heterogeneous material systems with a large design space, where physics-based repetitive numerical simulations may be required. Furthermore, conducting physical experiments over such a large design space can be both time-consuming and costly. To address these challenges, convolutional neural networks (CNNs) have become increasingly popular as a computationally feasible way to make high-fidelity predictions for various materials, based on simulation results or experimental data. CNNs are particularly useful for materials with complex microstructures that are difficult to characterize or quantify, especially when suitable descriptors are not available. However, these models often suffer from poor transferability and reduced robustness due to limited training data. One key issue in material prediction tasks is unbalanced data caused by the different costs of getting different material responses. This imbalance can lead to biased model predictions and poor generalization on unseen material structures. To overcome this challenge, we propose using multi-task learning (MTL) to provide deep learning models with more knowledge of material behaviors, specifically targeting the unbalanced data problem. MTL is a powerful technique that improves the performance of multiple related learning tasks by leveraging useful information among them. In the context of material prediction, MTL can be applied to jointly train the CNN model on multiple tasks, such as predicting displacement and strain energy. By simultaneously learning these related tasks, the model can better capture the underlying patterns and correlations between them, leading to more accurate and robust predictions.