Machine Learning Force Fields

Chemical Reviews, Journal Year: 2021, Volume and Issue: 121(16), P. 10142 - 10186

Published: March 11, 2021

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out reach due to complexity traditional electronic-structure methods. One most promising applications is construction ML-based force fields (FFs), with aim narrow gap between accuracy ab initio methods and efficiency classical FFs. The key idea learn statistical relation chemical structure potential energy without relying on a preconceived notion fixed bonds or knowledge about relevant interactions. Such universal ML approximations are principle only limited by quality quantity reference data used train them. This review gives an overview ML-FFs insights that can be obtained from core concepts underlying described detail, step-by-step guide for constructing testing them scratch given. text concludes discussion challenges remain overcome next generation ML-FFs.

Language: Английский

---

Atomistic Line Graph Neural Network for improved materials property predictions

npj Computational Materials, Journal Year: 2021, Volume and Issue: 7(1)

Published: Nov. 15, 2021

Abstract Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which critical distinguishing many structures. Furthermore, properties known be sensitive slight changes in angles. We present an Atomistic Line Neural Network (ALIGNN), a architecture that performs message passing both the interatomic graph its line corresponding demonstrate angle information can efficiently included, leading improved multiple prediction tasks. ALIGNN predicting 52 solid-state molecular available JARVIS-DFT, Materials project, QM9 databases. outperform some previously reported tasks better or comparable model training speed.

Language: Английский

---

Graph neural networks for materials science and chemistry

Communications Materials, Journal Year: 2022, Volume and Issue: 3(1)

Published: Nov. 26, 2022

Abstract Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict properties, accelerate simulations, design new structures, synthesis routes materials. Graph neural networks (GNNs) are one the fastest growing classes machine models. They particular relevance for as they directly work on a graph or structural representation molecules therefore have full access all relevant information required characterize In this Review, we provide overview basic principles GNNs, widely datasets, state-of-the-art architectures, followed by discussion wide range recent applications GNNs concluding with road-map further development application GNNs.

Language: Английский

---

Machine Learning for Electronically Excited States of Molecules

Chemical Reviews, Journal Year: 2020, Volume and Issue: 121(16), P. 9873 - 9926

Published: Nov. 19, 2020

Electronically excited states of molecules are at the heart photochemistry, photophysics, as well photobiology and also play a role in material science. Their theoretical description requires highly accurate quantum chemical calculations, which computationally expensive. In this review, we focus on not only how machine learning is employed to speed up such excited-state simulations but branch artificial intelligence can be used advance exciting research field all its aspects. Discussed applications for include dynamics simulations, static calculations absorption spectra, many others. order put these studies into context, discuss promises pitfalls involved techniques. Since latter mostly based chemistry provide short introduction electronic structure methods approaches nonadiabatic describe tricks problems when using them molecules.

Language: Английский

---

Machine Learning for Chemical Reactions

Chemical Reviews, Journal Year: 2021, Volume and Issue: 121(16), P. 10218 - 10239

Published: June 7, 2021

Machine learning (ML) techniques applied to chemical reactions have a long history. The present contribution discusses applications ranging from small molecule reaction dynamics computational platforms for planning. ML-based can be particularly relevant problems involving both computation and experiments. For one, Bayesian inference is powerful approach develop models consistent with knowledge Second, methods also used handle that are formally intractable using conventional approaches, such as exhaustive characterization of state-to-state information in reactive collisions. Finally, the explicit simulation networks they occur combustion has become possible machine-learned neural network potentials. This review provides an overview questions been addressed machine techniques, outlook challenges this diverse stimulating field. It concluded ML chemistry practiced conceived today potential transform way which field approaches reactions, research academic teaching.

Language: Английский

---

The Role of Machine Learning in the Understanding and Design of Materials

Journal of the American Chemical Society, Journal Year: 2020, Volume and Issue: 142(48), P. 20273 - 20287

Published: Nov. 10, 2020

Developing algorithmic approaches for the rational design and discovery of materials can enable us to systematically find novel materials, which have huge technological social impact. However, such requires a holistic perspective over full multistage process, involves exploring immense spaces, their properties, process engineering as well techno-economic assessment. The complexity all these options using conventional scientific seems intractable. Instead, tools from field machine learning potentially solve some our challenges on way design. Here we review chief advancements methods applications in design, followed by discussion main opportunities currently face together with future discovery.

Language: Английский

---

Neural Network Potential Energy Surfaces for Small Molecules and Reactions

Chemical Reviews, Journal Year: 2020, Volume and Issue: 121(16), P. 10187 - 10217

Published: Oct. 6, 2020

We review progress in neural network (NN)-based methods for the construction of interatomic potentials from discrete samples (such as ab initio energies) applications classical and quantum dynamics including reaction computational spectroscopy. The main focus is on building molecular potential energy surfaces (PES) internal coordinates that explicitly include all many-body contributions, even though some we limit degree coupling, due either to a desire cost or limited data. Explicit direct treatment contributions only practical sufficiently small molecules, which are therefore our primary focus. This includes molecules surfaces. consider direct, single NN PES fitting well more complex impose structure multibody representation) function, through architecture one by using multiple NNs. show how NNs effective representations with low-dimensional functions dimensionality reduction. NN-based approaches build PESs sums-of-product form important dynamics, ways treat symmetry, issues related sampling data distributions relation between errors observables. highlight combinations other ideas such permutationally invariant polynomials sums environment-dependent atomic have recently emerged powerful tools highly accurate relatively large reactive systems.

Language: Английский

---

Molecular excited states through a machine learning lens

Nature Reviews Chemistry, Journal Year: 2021, Volume and Issue: 5(6), P. 388 - 405

Published: May 20, 2021

Language: Английский

---

Perspective on integrating machine learning into computational chemistry and materials science

The Journal of Chemical Physics, Journal Year: 2021, Volume and Issue: 154(23)

Published: June 21, 2021

Machine learning (ML) methods are being used in almost every conceivable area of electronic structure theory and molecular simulation. In particular, ML has become firmly established the construction high-dimensional interatomic potentials. Not a day goes by without another proof principle published on how can represent predict quantum mechanical properties-be they observable, such as polarizabilities, or not, atomic charges. As is becoming pervasive simulation, we provide an overview atomistic computational modeling transformed incorporation approaches. From perspective practitioner field, assess common workflows to structure, dynamics, spectroscopy affected ML. Finally, discuss tighter lasting integration with chemistry materials science be achieved what it will mean for research practice, software development, postgraduate training.

Language: Английский

---

The OpenMolcas Web: A Community-Driven Approach to Advancing Computational Chemistry

Journal of Chemical Theory and Computation, Journal Year: 2023, Volume and Issue: 19(20), P. 6933 - 6991

Published: May 22, 2023

The developments of the open-source OpenMolcas chemistry software environment since spring 2020 are described, with a focus on novel functionalities accessible in stable branch package or via interfaces other packages. These span wide range topics computational and presented thematic sections: electronic structure theory, spectroscopy simulations, analytic gradients molecular optimizations, ab initio dynamics, new features. This report offers an overview chemical phenomena processes can address, while showing that is attractive platform for state-of-the-art atomistic computer simulations.

Language: Английский

---