AdsorbML - A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials

Aug 5, 2026

Upload by Finn

Computational catalysis relies on accurately determining adsorption energies between an adsorbate and a catalyst surface, a task that is traditionally handled using heuristics and researcher intuition to find low-energy configurations. With increasing needs for high-throughput screening, those approaches become inefficient and difficult to scale. This work leverages generalizable machine learning potentials to identify low-energy adsorbate-surface configurations more accurately and far more efficiently. The method provides adjustable accuracy-efficiency trade-offs, achieves the lowest-energy configuration 87.36% of the time, and delivers about a 2000× speedup. Benchmarking is standardized via the Open Catalyst Dense dataset, with nearly 1,000 diverse surfaces and ~100,000 unique configurations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Introduction

Adsorption energies in heterogeneous catalysis

Relaxation and optimization workflow (DFT)

Adsorption energy definition and equation

arXiv :2211 . 16486v3 [ cond-mat .mtrl-sci ] 15 Sep 2023 AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials Janice Lan∗ , 1 Aini Palizhati∗ ,2 Muhammed Shuaibi∗ , 1 Brandon M. Wood∗ , 1 Brook Wander,2 Abhishek Das, 1 Matt Uyttendaele, 1 C. Lawrence Zitnick†, 1 and Zachary W. Ulissi†2, 3 1 Fundamental AI Research (FAIR), Meta AI, Meta 2 Department of Chemical Engineering, Carnegie Mellon University 3 Scott Institute for Energy Innovation, Carnegie Mellon University Computational catalysis is playing an increasingly significant role in the design of catalysts across a wide range of applications. A common task for many computational methods is the need to accurately compute the adsorption energy for an adsorbate and a catalyst surface of interest. Traditionally, the identification of low energy adsorbate-surface configurations relies on heuristic methods and researcher intuition. As the desire to perform high-throughput screening increases, it becomes challenging to use heuristics and intuition alone. In this paper, we demonstrate 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, while achieving a ∼2000x speedup in computation. To standardize benchmarking, we introduce the Open Catalyst Dense dataset containing nearly 1,000 diverse surfaces and ∼ 100,000 unique configurations. INTRODUCTION The design of novel heterogeneous catalysts plays an essential role in the synthesis of everyday fuels and chemicals. To accommodate the growing demand for energy while combating climate change, efficient, low-cost catalysts are critical to the utilization of renewable energy [1– 4] . Given the enormity of the material design space, efficient screening methods are highly sought after [4– 7] . Computational catalysis offers the potential to screen vast numbers of materials to complement more time-and cost-intensive experimental studies. A critical task for many first-principles approaches to heterogeneous catalyst discovery is the calculation of adsorption energies. The adsorption energy is the energy associated with a molecule, or adsorbate, interacting with a catalyst surface. Adsorbates are often selected to capture the various steps, or intermediates, in a reaction pathway (e.g. *CHO in CO2 reduction) . Adsorption energy is calculated by finding the adsorbate-surface configuration that minimizes the structure’s overall energy. Thus, the adsorption energy is the global minimum energy across all potential adsorbate placements and configurations. These adsorption energies are the starting point for the calculation of the free energy diagrams to determine the most favorable reaction pathways on a catalyst surface [8] . It has been demonstrated that adsorption energies of reaction intermediates can be powerful ∗ Equal Contribution † Corresponding authors C.L.Z., email: [zitnick@meta.com](zitnick@meta.com) Z.W.U., email: [zulissi@andrew.cmu.edu](zulissi@andrew.cmu.edu) descriptors that correlate with experimental outcomes such as activity or selectivity [9–13] . This ability to predict trends in catalytic properties from first-principles is the basis for efficient catalyst screening approaches [1, 14] . Finding the adsorption energy presents a number of complexities. There are numerous potential binding sites for an adsorbate on a surface and for each binding site there are multiple ways to orient the adsorbate (see bottom-left in Figure 1) . When an adsorbate is placedon a catalyst’s surface, the adsorbate and surface atoms will interact with each other. To determine the adsorption energy for a specific adsorbate-surface configuration, the atom positions need to be relaxed until a local energy minimum is reached

FAQs

Why are adsorption energy calculations important in catalyst discovery?

Adsorption energies quantify the interaction between a molecule (adsorbate) and a catalyst surface. They are used as starting points for further thermodynamic analyses, such as free energy diagrams to identify favorable reaction pathways.

What challenges arise when finding the adsorption energy minimum?

Multiple binding sites and orientations create many candidate configurations, and determining the global minimum requires reliable sampling and relaxation. Density Functional Theory (DFT) relaxations are computationally expensive, making exhaustive search difficult at scale.

How does AdsorbML improve efficiency and accuracy?

AdsorbML uses generalizable machine learning potentials to identify low-energy adsorbate-surface configurations more accurately and efficiently than heuristic approaches. It supports accuracy-efficiency trade-offs and reports finding the lowest-energy configuration 87.36% of the time with roughly a 2000× speedup.

Aug 5, 2026

Upload by Finn