Machine learning-accelerated discovery and design of electrode materials and electrolytes for lithium ion batteries

G Xu, M Jiang, J Li, X Xuan, J Li, T Lu, L Pan - Energy Storage Materials, 2024 - Elsevier
With the development of artificial intelligence and the intersection of machine learning (ML)
and materials science, the reclamation of ML technology in the realm of lithium ion batteries …

How Does Structural Disorder Impact Heterogeneous Catalysts? The Case of Ammonia Decomposition on Non-stoichiometric Lithium Imide

F Mambretti, U Raucci, M Yang, M Parrinello - ACS Catalysis, 2024 - ACS Publications
Among the many catalysts suggested for ammonia decomposition, Li2NH has been shown
to be quite promising. In the recent past, we have performed extensive ab initio-quality …

Data-efficient fine-tuning of foundational models for first-principles quality sublimation enthalpies

H Kaur, F Della Pia, I Batatia, XR Advincula… - Faraday …, 2025 - pubs.rsc.org
Calculating sublimation enthalpies of molecular crystal polymorphs is relevant to a wide
range of technological applications. However, predicting these quantities at first-principles …

Anion-derived contact ion pairing as a unifying principle for electrolyte design

S Ilic, SN Lavan, JG Connell - Chem, 2024 - cell.com
Enabling new electrochemical technologies requires systems that can operate under ever-
more demanding conditions, and progress in energy storage applications reveals tantalizing …

Thermophysical properties of Molten FLiNaK: A moment tensor potential approach

N Rybin, D Maksimov, Y Zaikov, A Shapeev - Journal of Molecular Liquids, 2024 - Elsevier
Fluoride salts demonstrate significant potential for applications in next-generation nuclear
reactors, necessitating a comprehensive understanding of their thermophysical properties …

Machine-Learned Potentials by Active Learning from Organic Crystal Structure Prediction Landscapes

PWV Butler, R Hafizi, GM Day - The Journal of Physical Chemistry …, 2024 - ACS Publications
A primary challenge in organic molecular crystal structure prediction (CSP) is accurately
ranking the energies of potential structures. While high-level solid-state density functional …

A dual-cutoff machine-learned potential for condensed organic systems obtained via uncertainty-guided active learning

L Kahle, B Minisini, T Bui, JT First, C Buda… - Physical Chemistry …, 2024 - pubs.rsc.org
Machine-learned potentials (MLPs) trained on ab initio data combine the computational
efficiency of classical interatomic potentials with the accuracy and generality of the first …

Transferability of datasets between Machine-Learning Interaction Potentials

SP Niblett, P Kourtis, IB Magdău, CP Grey… - arXiv preprint arXiv …, 2024 - arxiv.org
With the emergence of Foundational Machine Learning Interatomic Potential (FMLIP)
models trained on extensive datasets, transferring data between different ML architectures …

Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly

F Zills, MR Schäfer, N Segreto… - The Journal of …, 2024 - ACS Publications
The field of machine learning potentials has experienced a rapid surge in progress, thanks
to advances in machine learning theory, algorithms, and hardware capabilities. While the …

On the design space between molecular mechanics and machine learning force fields

Y Wang, K Takaba, MS Chen, M Wieder, Y Xu… - arXiv preprint arXiv …, 2024 - arxiv.org
A force field as accurate as quantum mechanics (QM) and as fast as molecular mechanics
(MM), with which one can simulate a biomolecular system efficiently enough and …