On-the-fly machine learning force field generation: Application to melting points

Jinnouchi, Ryosuke; Karsai, Ferenc; Kresse, Georg

doi:10.1103/physrevb.100.014105

Cited by 351 publications

(379 citation statements)

References 66 publications

(97 reference statements)

Supporting

Mentioning

315

Contrasting

Order By: Relevance

“…Podryabinkin et al showed that their approach can identify various existing and hypothetical boron allotropes 20 . Finally, Jinnouchi et al demonstrated how ab initio molecular dynamics (AIMD) simulations of specific systems can be sped up by active learning of the computed forces (in a modified GAP framework), using the predicted error of the Gaussian process to select new datapoints and to improve the speed of AIMD 37,39 .…”

Section: Introductionmentioning

confidence: 99%

De novo exploration and self-guided learning of potential-energy surfaces

2019

View full text Add to dashboard Cite

Interatomic potential models based on machine learning (ML) are rapidly developing as tools for materials simulations. However, because of their flexibility, they require large fitting databases that are normally created with substantial manual selection and tuning of reference configurations. Here, we show that ML potentials can be built in a largely automated fashion, exploring and fitting potential-energy surfaces from the beginning (de novo) within one and the same protocol. The key enabling step is the use of a configuration-averaged kernel metric that allows one to select the few most relevant structures at each step. The resulting potentials are accurate and robust for the wide range of configurations that occur during structure searching, despite only requiring a relatively small number of single-point DFT calculations on small unit cells. We apply the method to materials with diverse chemical nature and coordination environments, marking a milestone toward the more routine application of ML potentials in physics, chemistry, and materials science.

show abstract

Section: Introductionmentioning

confidence: 99%

De novo exploration and self-guided learning of potential-energy surfaces

2019

View full text Add to dashboard Cite

show abstract

“…We also mention on-the-fly or "onlinetrained" ML potentials: [80][81][82] these start with a quantummechanical (again, normally DFT-based) MD simulation and train an ML potential while the simulation is being run. We also mention on-the-fly or "onlinetrained" ML potentials: [80][81][82] these start with a quantummechanical (again, normally DFT-based) MD simulation and train an ML potential while the simulation is being run.…”

Section: Ingredient 3: Regression Tools and Implementationsmentioning

confidence: 99%

“…We conclude this methodological overview by stressing that all methods discussed here lead to "offline-trained" ML potentials: one generates (and extensively validates) a suitable potential for a specific material, and then applies it without further modification. We also mention on-the-fly or "onlinetrained" ML potentials: [80][81][82] these start with a quantummechanical (again, normally DFT-based) MD simulation and train an ML potential while the simulation is being run. Numerical measures are put in place to monitor the degree of extrapolation (that is: do we need additional data at this point?…”

Section: Ingredient 3: Regression Tools and Implementationsmentioning

confidence: 99%

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

View full text Add to dashboard Cite

In pursuit of this goal, atomic-scale computer simulations have long been a central approach, and two major families of methods are routinely used today. On the one hand, there are quantum-mechanical simulations, in which we solve Schrödinger's equation for the electronic structure of molecular and periodic systems, most widely based on density-functional theory (DFT). [6][7][8] These methods provide (largely) reliable results for structural models of materials that normally contain a few tens or hundreds of atoms. State-of-the-art DFT methods can be applied to many material classes, and they are increasingly used for high-throughput screening and "in silico" (computer-based) design of materials: new compositions and previously unknown structures have been identified in DFT searches and subsequently experimentally realized. [5,[9][10][11] On the other hand, interatomic potential models ("force fields"), parameterizing interactions between atoms with (relatively) simple functional forms, are widely used in materials science to describe matter in molecular dynamics (MD) simulations. These simulations grant access to larger time and length scales, reaching system sizes of up to hundreds of thousands of atoms. [12] In parameterizing these potentials, a certain physical form of the atomic interactions is assumed, often in terms of bond distances, angles, and so on, and physical properties such as equilibrium lattice parameters or elastic constants enter the fitting of the potential. For this reason, such potentials are often called "empirical." They are several orders of magnitude faster than DFT, but necessarily less accurate and less easily transferable.In this Progress Report, we highlight recent developments in "machine-learned" interatomic potentials, which represent a rapidly growing field that promises to do away with the aforementioned trade-offs. Over the last year, there has been a surge of interest in machine learning (ML) methodology: part of it is due to the dramatic growth of ML throughout the scientific disciplines, and part of it is due to tangible success stories of ML-based interatomic potentials that are now beginning to emerge. We will argue that this is an exciting development with very practical implications, currently on the verge of moving from a somewhat specialized new technology to everyday applicability, poised to enhance and complement the communities' existing strengths in computational materials modeling. We will show selected applications of ML potentials to problems in materials science, discuss the current limitations (and possible pitfalls), and outline what we expect to be interesting directions for the development of the field in the coming years.Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materi...

show abstract

“…They benchmark the accuracy of the uncertainty prediction by maximum likelihood estimation which in turn can correct for correlations between resampled models and improve performance of the uncertainty estimation via a cross-validation procedure [120]. By tracking model uncertainty during the MD simulation, a call to the high-fidelity (but expensive) DFT calculation can made when the system drifts to a configuration where the model is uncertain in the energy/force prediction beyond a certain threshold [102,121,122]. Vandermause et al [123] sampled structures on-the-fly from AIMD and used an adaptive Bayesian inference method to automate the training of low-dimensional multiple element interatomic force fields.…”

Section: Iterative Improvement Of Ff Using Active and Transfer Learningmentioning

confidence: 99%

Machine learning for multi-fidelity scale bridging and dynamical simulations of materials

Batra

Sankaranarayanan

2020

J. Phys. Mater.

View full text Add to dashboard Cite

Molecular dynamics (MD) is a powerful and popular tool for understanding the dynamical evolution of materials at the nano and mesoscopic scales. There are various flavors of MD ranging from the high fidelity albeit computationally expensive ab-initio MD to relatively lower fidelity but much more efficient classical MD such as atomistic and coarse-grained models. Each of these different flavors of MD have been independently used by materials scientists to bring about breakthroughs in materials discovery and design. A significant gulf exists between the various MD flavors, each having varying levels of fidelity. The accuracy of DFT or ab-initio MD is generally much higher than that of classical atomistic simulations which is higher than that of coarse-grained models. Multi-fidelity scale bridging to combine the accuracy and flexibility of ab-initio MD with efficiency classical MD has been a longstanding goal. The advent of big-data analytics has brought to the forefront powerful machine learning methods that can be deployed to achieve this goal. Here, we provide our perspective on the challenges in multi-fidelity scale bridging and trace the developments leading up to the use of machine learning algorithms and data-science towards addressing this grand challenge. arXiv:2004.00232v1 [physics.comp-ph] 1 Apr 2020

show abstract

On-the-fly machine learning force field generation: Application to melting points

Cited by 351 publications

References 66 publications

De novo exploration and self-guided learning of potential-energy surfaces

De novo exploration and self-guided learning of potential-energy surfaces

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Machine learning for multi-fidelity scale bridging and dynamical simulations of materials

Contact Info

Product

Resources

About