Prof Ong gave a talk on “Discovering New Materials in a Fraction of the Time with Graph Networks” at the NVIDIA GTC 2021 conference. This talk discusses our recent work on using GPU-trained multi-fidelity graph networks, together with Bayseian optimization techniques, to discover novel materials.
Richard’s paper on “Metal-Insulator Transition in V2O3 with Intrinsic Defects” has just been published in Physical Review B! V2O3 is a material of potential interest for neuromorphic computing, i.e., computers that mimic biological brains and have the potential to be far more efficient than traditional von Neumann
architectures. A potential implementation utilizes metal insulator transitions (MITs) to implement “leaky, integrate, and fire” to emulate short-term memory. V2O3, which undergo a metal-insulator transition (MIT) at 165K, can be used to implement al for such devices as they exhibit a sudden collapse of insulating behavior under an external stimuli, and they can gradually recover their insulating state over time in the absence of the stimuli. This behavior is known as volatile resistive switching. Here, we show that the PBE + U functional provides the best compromise between accuracy and efficiency in calculating the properties related to the MIT between low-temperature and high-temperature V2O3. We use this functional to explore the various influences that intrinsic point defects will have on the MIT in V2O3.
This work is a collaboration with the Schuller group at UCSD as part of the Quantum Materials for Energy Efficient Neuromorphic Computing (QMEEN-C) center, an Energy Frontier Research Center funded by the Department of Energy.
Our collaborative work with the Meng (UCSD) and Clement (UCSB) groups on the discovery of the Na3-xY1-xZrxCl6 (NYZC) ion conductor has just been published in Nature Communications. While rechargeable solid-state sodium-ion batteries (SSSBs) promise to bring about safer and more energy-dense energy storage, the poor interfacial stability between existing solid electrolytes and typical oxide cathodes has limited their long-term cycling performance and practicality. Using DFT calculations and MD simulations with a machine learning interatomic potential, Swastika Banerjee and Ji Qi from the Materials Virtual Lab identified NYZC as a promising new ion conductor that is both electrochemically stable up to 3.8 V vs. Na/Na+ and chemically compatible with oxide cathodes. NYZC’s ionic conductivity of 6.6 × 10−5 S/cm at ambient temperature, several orders of magnitude higher than oxide coatings, is due to abundant Na vacancies and cooperative MCl6 rotation. A SSSB comprising a NaCrO2 + NYZC composite cathode, Na3PS4 electrolyte, and Na-Sn anode exhibits an exceptional first-cycle Coulombic efficiency of 97.1% at room temperature and can cycle over 1000 cycles with 89.3% capacity retention at 40 °C. Check out our article at this link.
Our collaborative work with Prof Hu’s group at Florida State University on “Tunable Lithium-Ion Transport in Mixed-Halide Argyrodites Li6-xPS5-xClBrx: An Unusual Compositional Space” has been published in Chemistry of Materials. In this work, we report a new compositional space of argyrodite superionic conductors, Li6−xPS5−xClBrx [0 ≤ x ≤ 0.8]. In particular, Li5.3PS4.3ClBr0.7 has a remarkably high ionic conductivity of 24 mS/cm at 25 °C and an extremely low lithium migration barrier of 0.155 eV that makes it highly promising for low-temperature operation. Using NMR and DFT calculations (performed by Swastika Banerjee from the Materials Virtual Lab), we show that bromination leads to co-occupancy of Cl-, Br- , and S2- at 4a/4d sites eventually resulting in a “liquid-like” Li-sublattice with a ﬂattened energy landscape when x approaches 0.7.
Chi Chen gave a talk at nanoHub’s Hands-on Data Science and Machine Learning Training Series on how to develop MatErials Graph Network (MEGNet) models for predicting various materials properties from crystal structure. He also demonstrates how the MEGNet framework can be adapted to work with multi-fidelity data sources to improve predictions on high-value small datasets (e.g., experimental data). Extensive examples are shown using Jupyter notebooks. The video is available on the Materials Virtual Lab Youtube Channel.
The megnet package used extensively in these tutorials can be found on Github.
Yunxing gave a talk at NanoHUB’s Hands-on Data Science and Machine Learning Training Series today on how to conveniently develop machine learning interatomic potentials (ML-IAPs) using the Materials Machine Learning (maml) library. ML-IAPs describe the potential energy surface using local environment descriptors and has been demonstrated to be able to achieve near-DFT accuracy with linear scaling with respect to the number of atoms. The recording of this talk is now available on the Materials Virtual Lab’s Youtube channel.
Our paper on “Learning properties of ordered and disordered materials from multi-fidelity data” has just been published in the inaugural issue of Nature Computational Science! In this work, we address two major impediments to ML for materials science. The first impediment is that valuable accurate data is much more expensive to obtain than less accurate data. Using multi-fidelity materials graph networks (MEGNet), we show that we can use the lower quality data to improve underlying structural representations in models, and in the process significantly improve predictions on smaller, more valuable data (e.g., experimental measurements). The second impediment is that making predictions on disordered materials, which is the vast majority of known materials, is much more difficult than on ordered materials. We show that the elemental representations (embeddings) learned by our MEGNet models can be used to directly model disordered materials.
Zhuoying’s paper on “Design Principles for Cation-Mixed Sodium Solid Electrolytes” is the first publication from the Materials Virtual Lab in 2021! All-solid-state sodium-ion batteries are highly promising for next-generation grid energy storage with improved safety. Published in Advanced Energy Materials, this work develops design rules for the highly promising family of cation-mixed Na superionic conductors Na3PnS4-Na4TtS4. We show that cation mixing results in the “worst of both worlds” in terms of electrochemical stability, but can potentially lead to improved ionic conductivity and moisture stability. In particular, the recently reported Na11Sn2PnS12 superionic conductors are shown to be stable and Na11Sn2AsS12 is identified as a hitherto unexplored stable sodium superionic conductor with higher Na + conductivity and better moisture stability than those already reported experimentally.
Our joint publication with Prof Hailong Chen’s group on “Multiprincipal Component P2-Na0.6(Ti0.2Mn0.2Co0.2Ni0.2Ru0.2)O2 as a High-Rate Cathode for Sodium-Ion Batteries” has just been published in JACS Au. In this work, we extended the “high-entropy” concept in metal alloys and ceramics to layered oxide cathode materials, which stablizes the crystal structure and enhances diffusion. Chi Chen from our group showed using AIMD calculations and NEB calculations that the high-entropy concept leads to a percolating network of low barrier pathways for fast, macroscopic Na diffusion, resulting in the observed high rate performance.
Prof Ong gave a talk at the Joule & Energy and AI Joint Online Symposium on our recent work on “Multi-fidelity Graph Networks forMaterials Property Predictions”. Predicting the properties of a material from the arrangement of its atoms is a fundamental goal in materials science. In recent years, machine learning (ML) on ab initio calculations has emerged as a new paradigm to provide rapid predictions of materials properties across vast chemical spaces. However, the performances of ML models are determined by the quantity and quality of data, which tend to be inversely correlated with each other. In this talk, we show that multi-fidelity materials graph networks can transcend this trade-off to achieve accurate predictions of the experimental band gaps of ordered and disordered materials to within 0.3-0.5 eV. Further, such models can be readily extended to predict the band gaps of disordered crystals to excellent agreement with experiments, addressing a major gap in the computational prediction of materials properties.
You can check out the two works discussed in the presentation at:
(1) Chen, C.; Zuo, Y.; Ye, W.; Li, X.; Ong, S. P. Multi-Fidelity Graph Networks for Machine Learning the Experimental Properties of Ordered and Disordered Materials. arXiv:2005.04338 [cond-mat] 2020. (Accepted in Principle for Nature Computational Materials)
(2) Chen, C.; Ye, W.; Zuo, Y.; Zheng, C.; Ong, S. P. Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals. Chem. Mater. 2019, 31 (9), 3564–3572. https://doi.org/10.1021/acs.chemmater.9b01294.
The MEGNet code is available at our Github repo at https://github.com/materialsvirtuallab/megnet.