1
|
Noordhoek K, Bartel CJ. Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials. NANOSCALE 2024. [PMID: 38470833 DOI: 10.1039/d3nr06468a] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/14/2024]
Abstract
The surface properties of solid-state materials often dictate their functionality, especially for applications where nanoscale effects become important. The relevant surface(s) and their properties are determined, in large part, by the material's synthesis or operating conditions. These conditions dictate thermodynamic driving forces and kinetic rates responsible for yielding the observed surface structure and morphology. Computational surface science methods have long been applied to connect thermochemical conditions to surface phase stability, particularly in the heterogeneous catalysis and thin film growth communities. This review provides a brief introduction to first-principles approaches to compute surface phase diagrams before introducing emerging data-driven approaches. The remainder of the review focuses on the application of machine learning, predominantly in the form of learned interatomic potentials, to study complex surfaces. As machine learning algorithms and large datasets on which to train them become more commonplace in materials science, computational methods are poised to become even more predictive and powerful for modeling the complexities of inorganic surfaces at the nanoscale.
Collapse
Affiliation(s)
- Kyle Noordhoek
- Department of Chemical Engineering and Materials Science, University of Minnesota, Minneapolis, MN, 55455, USA.
| | - Christopher J Bartel
- Department of Chemical Engineering and Materials Science, University of Minnesota, Minneapolis, MN, 55455, USA.
| |
Collapse
|
2
|
Du X, Damewood JK, Lunger JR, Millan R, Yildiz B, Li L, Gómez-Bombarelli R. Machine-learning-accelerated simulations to enable automatic surface reconstruction. NATURE COMPUTATIONAL SCIENCE 2023; 3:1034-1044. [PMID: 38177720 DOI: 10.1038/s43588-023-00571-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Accepted: 11/13/2023] [Indexed: 01/06/2024]
Abstract
Understanding material surfaces and interfaces is vital in applications such as catalysis or electronics. By combining energies from electronic structure with statistical mechanics, ab initio simulations can, in principle, predict the structure of material surfaces as a function of thermodynamic variables. However, accurate energy simulations are prohibitive when coupled to the vast phase space that must be statistically sampled. Here we present a bi-faceted computational loop to predict surface phase diagrams of multicomponent materials that accelerates both the energy scoring and statistical sampling methods. Fast, scalable and data-efficient machine learning interatomic potentials are trained on high-throughput density-functional-theory calculations through closed-loop active learning. Markov chain Monte Carlo sampling in the semigrand canonical ensemble is enabled by using virtual surface sites. The predicted surfaces for GaN(0001), Si(111) and SrTiO3(001) are in agreement with past work and indicate that the proposed strategy can model complex material surfaces and discover previously unreported surface terminations.
Collapse
Affiliation(s)
- Xiaochen Du
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - James K Damewood
- Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Jaclyn R Lunger
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Reisel Millan
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Bilge Yildiz
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Microsystems Technology Laboratories, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Lin Li
- Massachusetts Institute of Technology Lincoln Laboratory, Lexington, MA, USA
| | - Rafael Gómez-Bombarelli
- Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
| |
Collapse
|
3
|
van der Oord C, Sachs M, Kovács DP, Ortner C, Csányi G. Hyperactive learning for data-driven interatomic potentials. NPJ COMPUTATIONAL MATERIALS 2023; 9:168. [PMID: 38666057 PMCID: PMC11041776 DOI: 10.1038/s41524-023-01104-6] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 08/02/2023] [Indexed: 04/28/2024]
Abstract
Data-driven interatomic potentials have emerged as a powerful tool for approximating ab initio potential energy surfaces. The most time-consuming step in creating these interatomic potentials is typically the generation of a suitable training database. To aid this process hyperactive learning (HAL), an accelerated active learning scheme, is presented as a method for rapid automated training database assembly. HAL adds a biasing term to a physically motivated sampler (e.g. molecular dynamics) driving atomic structures towards uncertainty in turn generating unseen or valuable training configurations. The proposed HAL framework is used to develop atomic cluster expansion (ACE) interatomic potentials for the AlSi10 alloy and polyethylene glycol (PEG) polymer starting from roughly a dozen initial configurations. The HAL generated ACE potentials are shown to be able to determine macroscopic properties, such as melting temperature and density, with close to experimental accuracy.
Collapse
|
4
|
Shi X, Cheng D, Zhao R, Zhang G, Wu S, Zhen S, Zhao ZJ, Gong J. Accessing complex reconstructed material structures with hybrid global optimization accelerated via on-the-fly machine learning. Chem Sci 2023; 14:8777-8784. [PMID: 37621421 PMCID: PMC10445438 DOI: 10.1039/d3sc02974c] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2023] [Accepted: 07/13/2023] [Indexed: 08/26/2023] Open
Abstract
The complex reconstructed structure of materials can be revealed by global optimization. This paper describes a hybrid evolutionary algorithm (HEA) that combines differential evolution and genetic algorithms with a multi-tribe framework. An on-the-fly machine learning calculator is adopted to expedite the identification of low-lying structures. With a superior performance to other well-established methods, we further demonstrate its efficacy by optimizing the complex oxidized surface of Pt/Pd/Cu with different facets under (4 × 4) periodicity. The obtained structures are consistent with experimental results and are energetically lower than the previously presented model.
Collapse
Affiliation(s)
- Xiangcheng Shi
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
- Department of Chemistry, National University of Singapore 3 Science Drive 3 Singapore 117543 Republic of Singapore
| | - Dongfang Cheng
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Ran Zhao
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Gong Zhang
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Shican Wu
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Shiyu Zhen
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Zhi-Jian Zhao
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- Haihe Laboratory of Sustainable Chemical Transformations Tianjin 300192 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
| | - Jinlong Gong
- School of Chemical Engineering and Technology, Key Laboratory for Green Chemical Technology of Ministry of Education, Tianjin University Tianjin 300072 China
- Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) Tianjin 300072 China
- Haihe Laboratory of Sustainable Chemical Transformations Tianjin 300192 China
- National Industry-Education Platform of Energy Storage, Tianjin University 135 Yaguan Road Tianjin 300350 China
- Joint School of National University of Singapore and Tianjin University, International Campus of Tianjin University Binhai New City Fuzhou 350207 Fujian China
| |
Collapse
|
5
|
Li H, Jiao Y, Davey K, Qiao SZ. Data-Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts. Angew Chem Int Ed Engl 2023; 62:e202216383. [PMID: 36509704 DOI: 10.1002/anie.202216383] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 12/11/2022] [Accepted: 12/12/2022] [Indexed: 12/15/2022]
Abstract
The design of heterogeneous catalysts is necessarily surface-focused, generally achieved via optimization of adsorption energy and microkinetic modelling. A prerequisite is to ensure the adsorption energy is physically meaningful is the stable existence of the conceived active-site structure on the surface. The development of improved understanding of the catalyst surface, however, is challenging practically because of the complex nature of dynamic surface formation and evolution under in-situ reactions. We propose therefore data-driven machine-learning (ML) approaches as a solution. In this Minireview we summarize recent progress in using machine-learning to search and predict (meta)stable structures, assist operando simulation under reaction conditions and micro-environments, and critically analyze experimental characterization data. We conclude that ML will become the new norm to lower costs associated with discovery and design of optimal heterogeneous catalysts.
Collapse
Affiliation(s)
- Haobo Li
- School of Chemical Engineering and Advanced Materials, The University of Adelaide, Adelaide, SA 5005, Australia
| | - Yan Jiao
- School of Chemical Engineering and Advanced Materials, The University of Adelaide, Adelaide, SA 5005, Australia
| | - Kenneth Davey
- School of Chemical Engineering and Advanced Materials, The University of Adelaide, Adelaide, SA 5005, Australia
| | - Shi-Zhang Qiao
- School of Chemical Engineering and Advanced Materials, The University of Adelaide, Adelaide, SA 5005, Australia
| |
Collapse
|
6
|
Wanzenböck R, Arrigoni M, Bichelmaier S, Buchner F, Carrete J, Madsen GKH. Neural-network-backed evolutionary search for SrTiO 3(110) surface reconstructions. DIGITAL DISCOVERY 2022; 1:703-710. [PMID: 36324606 PMCID: PMC9549766 DOI: 10.1039/d2dd00072e] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/04/2022] [Accepted: 08/23/2022] [Indexed: 12/03/2022]
Abstract
The determination of atomic structures in surface reconstructions has typically relied on structural models derived from intuition and domain knowledge. Evolutionary algorithms have emerged as powerful tools for such structure searches. However, when density functional theory is used to evaluate the energy the computational cost of a thorough exploration of the potential energy landscape is prohibitive. Here, we drive the exploration of the rich phase diagram of TiOx overlayer structures on SrTiO3(110) by combining the covariance matrix adaptation evolution strategy (CMA-ES) and a neural-network force field (NNFF) as a surrogate energy model. By training solely on SrTiO3(110) 4×1 overlayer structures and performing CMA-ES runs on 3×1, 4×1 and 5×1 overlayers, we verify the transferability of the NNFF. The speedup due to the surrogate model allows taking advantage of the stochastic nature of the CMA-ES to perform exhaustive sets of explorations and identify both known and new low-energy reconstructions. The covariance matrix adaptation evolution strategy (CMA-ES) and a fully automatically differentiable, transferable neural-network force field are combined to explore TiOx overlayer structures on SrTiO3(110) 3×1, 4×1 and 5×1 surfaces.![]()
Collapse
Affiliation(s)
- Ralf Wanzenböck
- Institute of Materials Chemistry, TU Wien, 1060 Vienna, Austria
| | - Marco Arrigoni
- Institute of Materials Chemistry, TU Wien, 1060 Vienna, Austria
| | | | - Florian Buchner
- Institute of Materials Chemistry, TU Wien, 1060 Vienna, Austria
| | - Jesús Carrete
- Institute of Materials Chemistry, TU Wien, 1060 Vienna, Austria
| | | |
Collapse
|