Catalyst Discovery

Catalyst discovery, the process of identifying new materials for accelerating chemical reactions, is undergoing a revolution driven by artificial intelligence. Current research heavily utilizes machine learning, particularly graph neural networks (GNNs) and large language models (LLMs), to predict catalyst properties and design novel structures, often incorporating Bayesian optimization for efficient exploration of chemical space. These advancements aim to significantly reduce the time and cost associated with traditional trial-and-error methods, accelerating progress in sustainable energy technologies and other crucial applications. Explainable AI techniques are also being integrated to enhance the interpretability of these models and provide chemical insights.

Papers

October 22, 2024

Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent
Janghoon Ock, Tirtha Vinchurkar, Yayati Jadhav, Amir Barati Farimani
Automatic Identification Catalyst Design User Defined Configuration Catalyst Discovery Adsorption Energy Adsorbate Placement

July 19, 2024

Generative Language Model for Catalyst Discovery
Dong Hyeon Mok, Seoin Back
Generative Language Model Catalyst Design Catalyst Discovery

July 10, 2024

A Machine Learning and Explainable AI Framework Tailored for Unbalanced Experimental Catalyst Discovery
Parastoo Semnani, Mihail Bogojeski, Florian Bley, Zizheng Zhang, Qiong Wu, Thomas Kneib, Jan Herrmann, Christoph Weisser, Florina Patcas, Klaus-Robert Müller
Machine Learning Catalyst Design Catalyst Discovery Explainable AI Framework

May 13, 2024

CataLM: Empowering Catalyst Design Through Large Language Models
Ludi Wang, Xueqing Chen, Yi Du, Yuanchun Zhou, Yang Gao, Wenjuan Cui
Catalyst Design Knowledge Exploration Catalyst Discovery

April 18, 2024

Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning
Jie Chen, Pengfei Ou, Yuxin Chang, Hengrui Zhang, Xiao-Yan Li, Edward H. Sargent, Wei Chen
Representation Learning Multi Objective Bayesian Optimization Catalyst Design Atomistic Machine Learning Catalyst Discovery

April 5, 2024

Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery
Patrick Geitner
Energy Storage Molecular Modeling Geometric Neural Network Catalyst Discovery Open Catalyst

February 15, 2024

ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback
Henry W. Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V. Olarte, Udishnu Sanyal, Conrad Johnston, Hongbin Liu, Heng Ji, Sutanay Choudhury
Large Language Model Heuristic Search Catalyst Design Computational Chemistry Quantum Chemistry Knowledge Space Catalyst Discovery Large Scale Screening

September 26, 2022

Learned Force Fields Are Ready For Ground State Catalyst Discovery
Michael Schaarschmidt, Morgane Riviere, Alex M. Ganose, James S. Spencer, Alexander L. Gaunt, James Kirkpatrick, Simon Axelrod, Peter W. Battaglia, Jonathan Godwin
Force Field Catalyst Design Catalyst Discovery

September 15, 2022

Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based Single-Atom Alloy Catalysts for CO2 Reduction Reaction
Chen Liang, Bowen Wang, Shaogang Hao, Guangyong Chen, Pheng-Ann Heng, Xiaolong Zou
Human Prediction First Principle Mixture Density Network Catalyst Discovery Adsorption Energy

March 18, 2022

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations
Anuroop Sriram, Abhishek Das, Brandon M. Wood, Siddharth Goyal, C. Lawrence Zitnick
Graph Neural Network Pipeline Parallelism Atomic Simulation Catalyst Discovery Open Catalyst

Catalyst Discovery

Papers

Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent

Generative Language Model for Catalyst Discovery

A Machine Learning and Explainable AI Framework Tailored for Unbalanced Experimental Catalyst Discovery

CataLM: Empowering Catalyst Design Through Large Language Models

Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning

Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery

ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback

Learned Force Fields Are Ready For Ground State Catalyst Discovery

Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based Single-Atom Alloy Catalysts for CO2 Reduction Reaction

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations