Infusing Theory into Deep Learning for Interpretable Reactivity Prediction

Abstract

Despite recent advances of data acquisition and algorithms development, machine learning (ML) faces tremendous challenges to being adopted in practical catalyst design, largely due to its limited generalizability and poor explainability. Here, we develop a theory-infused neural network (TinNet) approach that integrates deep learning algorithms with the well-established $d$-band theory of chemisorption for reactivity prediction of transition-metal surfaces. With simple adsorbates (e.g., *OH, *O, and *N) at active site ensembles as representative descriptor species, we demonstrate that the TinNet is on par with purely data-driven ML methods in prediction performance, while being inherently interpretable. Incorporation of scientific knowledge of physical interactions into learning from data sheds further light on the nature of chemical bonding and opens up new avenues for ML discovery of novel motifs with desired catalytic properties.

References in corpus (5)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Beyond scaling relations for the description of catalytic materials
• An Atomistic Machine Learning Package for Surface Science and Catalysis
• Artificial intelligence real-time prediction and physical interpretation of atomic binding energies in nano-scale metal clusters

Cited by in corpus (1)

• Predicting binding motifs of complex adsorbates using machine learning with a physics-inspired graph representation