Porous media, ranging from bones to concrete and from batteries to architected lattices, pose difficult challenges in fully harnessing for engineering applications due to their complex and variable structures. Accurate and rapid assessment of their mechanical behavior is both challenging and essential, and traditional methods such as destructive testing and finite element analysis can be costly, computationally demanding, and time consuming. Machine learning (ML) offers a promising alternative for predicting mechanical behavior by leveraging data-driven correlations. However, with such structural complexity and diverse morphology among porous media, the question becomes how to effectively characterize these materials to provide robust feature spaces for ML that are descriptive, succinct, and easily interpreted. Here, we developed an automated methodology to determine porous material strength. This method uses scalar morphological descriptors, known as Minkowski functionals, to describe the porous space. From there, we conduct uniaxial compression experiments for generating material stress-strain curves, and then train an ML model to predict the curves using said morphological descriptors. This framework seeks to expedite the analysis and prediction of stress-strain behavior in porous materials and lay the groundwork for future models that can predict mechanical behaviors beyond compression.

Advancements in deep learning (DL) and machine learning (ML) have improved the ability to model complex, nonlinear relationships, such as those encountered in complex material inverse problems. However, the effectiveness of these methods often depends on large datasets, which are not always available. In this study, the incorporation of domain-specific knowledge of the mechanical behaviour of material microstructures is investigated to evaluate the effect on the predictive performance of the models in data-scarce scenarios. To overcome data limitations, a two-step framework, learning latent hardening (LLH), is proposed. In the first step of LLH, a deep neural network (DNN) is employed to reconstruct full stress–strain curves from randomly selected portions of the stress–strain curves to capture the latent mechanical response of a material based on key microstructural features. In the second step of LLH, the results of the reconstructed stress–strain curves are leveraged to predict key microstructural features of porous materials. The performance of six DL and/or ML models trained with and without domain knowledge are compared: convolutional neural networks (CNNs), DNN, extreme gradient boosting (XGBoost), K-nearest neighbours (KNN), long short-term memory (LSTM) and random forest (RF). The results from the models with domain-specific information consistently achieved higher 𝑅2 values compared to models without prior knowledge. When the models did not include domain knowledge, meaningful patterns in the model result, such as the link between stress–strain behaviour and underlying microstructural changes not being recognized, while those enhanced with domain knowledge insights showed better feature selection, in which they identified key stress–strain characteristics that are most relevant for predicting microstructure. These findings reveal the critical role domain-specific knowledge can provide in guiding DL models, further highlighting the need to combine domain expertise with data-driven approaches to achieve reliable and accurate outcomes in materials science and related fields.