A Hybrid Machine Learning Framework for Predicting Hydrogen Storage Capacities in Metal Hydrides: Unsupervised Feature Learning with Deep Neural Networks

Abstract

In this study, we present a sophisticated hybrid machine-learning framework that significantly improves the accuracy of predicting hydrogen storage capacities in metal hydrides. This is a critical challenge due to the scarcity of experimental data and the complexity of high-dimensional feature spaces. Our approach employs the power of unsupervised learning through the use of a state-of-the-art autoencoder. This autoencoder is trained on elemental descriptors obtained from the Mendeleev software, enabling the extraction of a meaningful and lower-dimensional latent space from the input data. This latent representation serves as the basis for our deep multilayer perceptron (MLP) model, which consists of five layers and shows good precision in predicting hydrogen storage capacities. Furthermore, our results show very good agreement with the results obtained with density functional theory (DFT). In addition to addressing the limitations caused by limited and unevenly distributed data in the field of hydrogen storage materials, we also focus on discovering new materials that show promising opportunities for hydrogen storage. These materials were identified using both feature-based approaches and predictions generated by a large language model (LLM). A significant highlight of this work is the integration of a decoder-only LLM based on GPT-2, which is fine-tuned for materials generation for hydrogen storage. Using such an approach, we have discovered new hydrogen storage materials with a selected subset subsequently validated through density functional theory (DFT) calculations.