Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study

2025-10-02

AI Summary

Current electrocatalysts for hydrogen storage suffer from insufficient activity and prohibitively high costs, particularly for the hydrogen evolution reaction (HER). Method: We propose a novel inverse materials design paradigm leveraging generative flow networks (GFlowNets), the first application of GFlowNets to catalyst discovery. Our framework integrates machine-learned models predicting formation energy and hydrogen adsorption energy to conditionally generate and globally optimize crystal surface structures targeting key catalytic performance metrics—e.g., low overpotential and high intrinsic activity. The method balances generation diversity with convergence, enabling efficient navigation of vast compositional and structural spaces. Contribution/Results: In a proof-of-concept study, the model autonomously identified platinum as the optimal HER catalyst without prior knowledge—validating the framework’s physical fidelity and predictive power. This work establishes a scalable, generative AI-driven approach for rational design of cost-effective, high-performance HER catalysts—and extends naturally to oxygen evolution reaction (OER) systems.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Efficient and inexpensive energy storage is essential for accelerating the adoption of renewable energy and ensuring a stable supply, despite fluctuations in sources such as wind and solar. Electrocatalysts play a key role in hydrogen energy storage (HES), allowing the energy to be stored as hydrogen. However, the development of affordable and high-performance catalysts for this process remains a significant challenge. We introduce Catalyst GFlowNet, a generative model that leverages machine learning-based predictors of formation and adsorption energy to design crystal surfaces that act as efficient catalysts. We demonstrate the performance of the model through a proof-of-concept application to the hydrogen evolution reaction, a key reaction in HES, for which we successfully identified platinum as the most efficient known catalyst. In future work, we aim to extend this approach to the oxygen evolution reaction, where current optimal catalysts are expensive metal oxides, and open the search space to discover new materials. This generative modeling framework offers a promising pathway for accelerating the search for novel and efficient catalysts.

Problem

• Designing affordable high-performance electrocatalysts for hydrogen storage
• Developing generative models to discover efficient catalyst crystal surfaces
• Accelerating discovery of novel catalysts beyond expensive metal oxides

Innovation

• Generative model designs efficient catalyst crystal surfaces
• Uses machine learning predictors for formation energy
• Demonstrated with hydrogen evolution reaction case study