Tag: machine learning

Presentations

NUS Seminar Talk on “Universal Machine Learning Models for Unconstrained Materials Design”

Prof Ong gave an invited seminar talk at the National University of Singapore on Jul 5 2023. In this talk, Prof Ong discusses the different ways in which machine learning (ML) can be used to improve or accelerate the various steps of in silico materials design. The general goal is to preserve the universality and accuracy of ab initio approaches as far as possible while achieving orders of magnitude speed-ups and improved scaling. Prof Ong shared his view that graph deep learning models trained on large diverse materials datasets, such as the M3GNet universal potential, are the “foundation” models for materials science. He further argues that the most robust approach is to replace the smallest, most expensive step in the materials design workflow with ML and preserve as much as the physics of thermodynamics, kinetics, etc. in the computation of materials properties.

Announcements

Materials Graph Library

We are excited to announce that Materials Graph Library (matgl), our Deep Graph Library/PyTorch reimplementation of the MatErials Graph Network (MEGNet) and Materials 3-body Graph Network (M3GNet) models, is now ready for widespread beta testing! We finally achieved near-feature parity with the original implementations in Tensorflow after months of hard work. The new MatGL includes retrained models of the M3GNet universal potential and the MEGNet formation energy and multi-fidelity band gap models. We have also taken the trouble to include example notebooks to get users started quickly. We believe this new implementation will be more future-proof and extensible. Feedback/issue reports are definitely welcome. This is a collaborative effort between the Materials Virtual Lab and Intel Labs.

Publications

Multi-scale investigation of MoNbTi and TaNbTi MPEAs

Hui’s swansong collaborative work on “Multi-scale investigation of short-range order and dislocation glide in MoNbTi and TaNbTi multi-principal element alloys” is now out in npj Computational Materials! This is a really exciting work that showcases an electron (DFT) to atom (machine learning interatomic potentials) to continuum (phase field dislocation dynamics) approach to the study of materials. It is a collaborative work between Hui and Lauren Fey of the group of Irene Beyerlein at UC Santa Barbara. Refractory multi-principal element alloys (RMPEAs) are promising materials for high-temperature structural applications. In this work, we performed an electron-to-atom-to-continuum study of the role of short-range ordering (SRO) on dislocation glide in the MoNbTi and TaNbTi RMPEAs. Monte carlo/molecular dynamics simulations with a moment tensor potential show that MoNbTi exhibits a much greater degree of SRO than TaNbTi and the local composition has a direct effect on the unstable stacking fault energies (USFEs). From mesoscale phase-field dislocation dynamics simulations, we find that increasing SRO leads to higher mean USFEs and stress required for dislocation glide. The gliding dislocations experience significant hardening due to pinning and depinning caused by random compositional fluctuations, with higher SRO decreasing the degree of USFE dispersion and hence, amount of hardening. […]

Publications

The intercalation chemistry of DRX-Li3V2O5 anode

Xingyu’s swansong work in the Materials Virtual Lab, “Intercalation Chemistry of the Disordered Rocksalt Li3V2O5 Anode from Cluster Expansions and Machine Learning Interatomic Potentials” has been published in Chemistry of Materials! We revisited the intercalation chemistry of the highly promising DRX-Li3V2O5 using machine learning-based computational techniques that enable much larger scale simulations. DRX Li3V2O5 is a promising anode candidate for rechargeable lithium-ion batteries because of its low voltage, high rate capability, and good cycling stability. In contrast to previous DFT studies, we show that insertion of Li primarily occurs in the tetrahedral sites and that the voltage profile depends critically on the initial Li/V disorder. MD simulations also show that DRX-Li3V2O5 has a fast Li diffusivity, which depends on the concentration of Li. We propose tuning the Li:V ratio as a means of trading off increased lithiation capacity and decreased anode voltage in this system. This work provides in-depth insights into the high-performance DRX-Li3V2O5 anode and paves the way for the discovery of other disordered anode materials. Check out the work here.

Publications

Matterverse.ai and M3GNet Universal IAP

Dr Chi Chen’s swansong work in our group, “A Universal Graph Deep Learning Potential for the Periodic Table” is now published in Nature Computational Science! Interatomic potentials (IAPs), which describe the potential energy surface of atoms, are a fundamental input for atomistic simulations. However, existing IAPs are either fitted to narrow chemistries or too inaccurate for general applications. In this work, we combine graph neural networks with traditional 3-body interactions to develop a flexible, yet accurate architecture for machine learning of materials properties. Using the massive database of structural relaxations performed by the Materials Project over the past ten years, we train a universal IAP for 89 elements of the periodic table with broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces. Using the new capabilities of the M3GNet universal IAP, we are proud to launch matterverse.ai, a ML database of yet-to-be-synthesized materials. Matterverse.ai currently contains about 31 million hypothetical crystal structures, of which about 1.8 million materials were identified to be potentially stable. The database also provides ML properties using state-of-the-art multi-fidelity MEGNet models, such as experimental, HSE and PBE band gaps, bulk and shear moduli, etc. Check out the article here. […]

Publications

Interfacial Stability of Lithium Sulfur Batteries

Congratulations to Manas Likhit Holekevi Chandrappa, Ji Qi, Chi Chen and Swastika Banerjee on the publication of “Thermodynamics and Kinetics of the Cathode−Electrolyte Interface in All-Solid-State Li−S Batteries” in the Journal of the American Chemical Society! Lithium−sulfur batteries (LSBs) use cheap and abundant sulfur in place of expensive metal-based cathodes. Using a solid electrolyte in place of traditional liquid electrolytes mitigates polysulfide shuttling, a key impediment to LSB commercialization. In this work, we present a comprehensive study of the thermodynamics and kinetics of the cathode−electrolyte interface in all-solid-state LSBs. Using DFT calculations, we show that among the major solid electrolyte chemistries (oxides, sulfides, nitrides, and halides), sulfides are the most stable solid electrolytes against the S cathode, as well as the most promising buffer layers if the use of other SE chemistries is desired. Finally, MD simulations with an accurate machine learning interatomic potential revealed that the most stable Li3PS4(100)/S interfaces form 2D channels with lower activation barriers for Li diffusion. These results provide critical new insights into the cathode−electrolyte interface design for next-generation all-solid-state LSBs. We gratefully acknowledge Nissan Motor Inc and Nissan North America for their generous support for this work! This work has been published open access […]

Presentations

CCMS Summer Institute Lecture 2022

Graphs are a natural way to represent atoms and bonds. In this lecture titled “Mathematical Graphs as a Representation for Materials”, Prof Shyue Ping Ong introduces the basics of graph deep learning and its application in materials science. MatErials Graph Networks (MEGNet) models have immense flexibility and expressiveness that can be adapted to datasets of diverse quality and quantity. We also demonstrate how the application of simple principles like energy minimization or interatomic development with materials graph models with 3-body interactions (M3GNet) can be used in the discovery of new materials **without** ab initio calculations, paving the way for massive-scale computational materials design. Prof Ong also introduces the matterverse.ai initiative, an open initiative to use ML to greatly expand the explorable matterverse. This lecture also includes two hands-on tutorials using Google Colab to demonstrate key concepts and the application of MEGNet and M3GNet models for property predictions and crystal structure relaxation. This Lecture is part of the Lawrence Livermore National Laboratory (LLNL) Computational Chemistry & Materials Science (CCMS) Summer Institute held from June 6 to August 12, 2022. The program offers graduate students the opportunity to work directly with leading LLNL researchers on the development and application of cutting-edge methods […]

Publications

Dislocation mobility in refractory high-entropy alloys

Our collaborative paper with the Ritchie and Asta groups on “Atomistic simulations of dislocation mobility in refractory high-entropy alloys (RHEAs) and the effect of chemical short-range order” has been published in Nature Communications! RHEAs are designed for high elevated-temperature strength, with both edge and screw dislocations playing an important role in plastic deformation. Using the highly accurate machine learning interatomic potential developed by MAVRL alum Dr Yunxing Zuo, we investigate mechanisms underlying the mobilities of screw and edge dislocations in the bcc MoNbTaW RHEA over a wide temperature range using MD simulations, and how these mechanisms are affected by the presence of short range order. We show that the mobility of edge dislocations is enhanced by SRO, while the rate of double-kink nucleation in the motion of screw dislocations is reduced. We also found a cross-slip locking mechanism for the motion of screws, which provides for extra strengthening for bcc RHEAs. Check out this work at this link.