Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent
- URL: http://arxiv.org/abs/2410.16658v1
- Date: Tue, 22 Oct 2024 03:19:16 GMT
- Title: Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent
- Authors: Janghoon Ock, Tirtha Vinchurkar, Yayati Jadhav, Amir Barati Farimani,
- Abstract summary: Adsorb-Agent is a Large Language Model (LLM) agent designed to efficiently derive system-specific stable adsorbate-catalyst configurations.
We demonstrate its performance using two example systems, NNH-CuPd3 (111) and NNH-Mo3Pd (111), for the Nitrogen Reduction Reaction (NRR), a sustainable alternative to the Haber-Bosch process.
- Score: 5.812284760539713
- License:
- Abstract: Adsorption energy is a key reactivity descriptor in catalysis, enabling the efficient screening of potential catalysts. However, determining adsorption energy involves comparing the energies of multiple adsorbate-catalyst configurations, which is computationally demanding due to a large number of possible configurations. Current algorithmic approaches typically enumerate adsorption sites and configurations without leveraging theoretical insights to guide the initial setup. In this work, we present Adsorb-Agent, a Large Language Model (LLM) agent designed to efficiently derive system-specific stable adsorption configurations with minimal human intervention. Adsorb-Agent leverages built-in knowledge and emergent reasoning capabilities, significantly reducing the number of initial configurations required while improving accuracy in predicting the minimum adsorption energy. We demonstrate its performance using two example systems, NNH-CuPd3 (111) and NNH-Mo3Pd (111), for the Nitrogen Reduction Reaction (NRR), a sustainable alternative to the Haber-Bosch process. Adsorb-Agent outperforms conventional "heuristic" and "random" algorithms by identifying lower-energy configurations with fewer initial setups, reducing computational costs while enhancing accuracy. This highlights its potential to accelerate catalyst discovery.
Related papers
- Explainable Data-driven Modeling of Adsorption Energy in Heterogeneous Catalysis [6.349503549199403]
This study aims to bridge the gap between physics-based studies and data-driven methodologies.
We employ two XAI techniques: Post-hoc XAI analysis and Symbolic Regression.
Our work establishes a robust framework that integrates machine learning techniques with XAI.
arXiv Detail & Related papers (2024-05-30T18:06:14Z) - Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning [17.00084254889438]
High-performance catalysts are crucial for sustainable energy conversion and human health.
The discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and composition spaces.
arXiv Detail & Related papers (2024-04-18T18:11:06Z) - ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback [37.06094829713273]
Discovery of new catalysts is essential for the design of new and more efficient chemical processes.
We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations.
arXiv Detail & Related papers (2024-02-15T21:33:07Z) - AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse
Catalysts Design [0.0]
A central challenge of the clean energy transition is the development of catalysts for low-emissions technologies.
Recent advances in Machine Learning for quantum chemistry drastically accelerate the computation of catalytic activity descriptors.
Here we introduce AdsorbRL, a Deep Reinforcement Learning agent aiming to identify potential catalysts given a multi-objective binding energy target.
arXiv Detail & Related papers (2023-12-04T19:44:04Z) - EKGNet: A 10.96{\mu}W Fully Analog Neural Network for Intra-Patient
Arrhythmia Classification [79.7946379395238]
We present an integrated approach by combining analog computing and deep learning for electrocardiogram (ECG) arrhythmia classification.
We propose EKGNet, a hardware-efficient and fully analog arrhythmia classification architecture that archives high accuracy with low power consumption.
arXiv Detail & Related papers (2023-10-24T02:37:49Z) - On the importance of catalyst-adsorbate 3D interactions for relaxed
energy predictions [98.70797778496366]
We investigate whether it is possible to predict a system's relaxed energy in the OC20 dataset while ignoring the relative position of the adsorbate.
We find that while removing binding site information impairs accuracy as expected, modified models are able to predict relaxed energies with remarkably decent MAE.
arXiv Detail & Related papers (2023-10-10T14:57:04Z) - AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using
Generalizable Machine Learning Potentials [8.636519538557001]
We show machine learning potentials can be leveraged to identify low energy adsorbate-surface configurations more accurately and efficiently.
Our algorithm provides a spectrum of trade-offs between accuracy and efficiency, with one balanced option finding the lowest energy configuration 87.36% of the time.
arXiv Detail & Related papers (2022-11-29T18:54:55Z) - Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based
Single-Atom Alloy Catalysts for CO2 Reduction Reaction [61.9212585617803]
Graph neural networks (GNNs) have drawn more and more attention from material scientists.
We develop a multi-task (MT) architecture based on DimeNet++ and mixture density networks to improve the performance of such task.
arXiv Detail & Related papers (2022-09-15T13:52:15Z) - Improving Molecular Representation Learning with Metric
Learning-enhanced Optimal Transport [49.237577649802034]
We develop a novel optimal transport-based algorithm termed MROT to enhance their generalization capability for molecular regression problems.
MROT significantly outperforms state-of-the-art models, showing promising potential in accelerating the discovery of new substances.
arXiv Detail & Related papers (2022-02-13T04:56:18Z) - Optimizing Molecules using Efficient Queries from Property Evaluations [66.66290256377376]
We propose QMO, a generic query-based molecule optimization framework.
QMO improves the desired properties of an input molecule based on efficient queries.
We show that QMO outperforms existing methods in the benchmark tasks of optimizing small organic molecules.
arXiv Detail & Related papers (2020-11-03T18:51:18Z) - Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable
Edge Computing Systems [87.4519172058185]
An effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied.
A novel multi-agent meta-reinforcement learning (MAMRL) framework is proposed to solve the formulated problem.
Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost.
arXiv Detail & Related papers (2020-02-20T04:58:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.