Machine Learning Interatomic Potentials (MLIPs) for Energy Materials
This project will develop machine learning inter-atomic potentials (MLIPs) for molecular materials and organic-inorganic interfaces relevant to energy storage technology and medicinal applications. The field of MLIPs is rapidly evolving, and it is poised to become central to the future of atomistic simulations. The efficiency and accuracy of MLIPs have been thoroughly studied on fixed train/test datasets, but the performance of these models in actual molecular dynamics (MD) remains poorly understood. Condensed phase molecular systems are particularly challenging to model owing to a large difference in scale between intra- and inter-molecular interactions. This project will test the stability and accuracy of General-purpose potentials (GPP) on molecular condensed phase applications, explore ways to enhance their accuracy in describing inter-molecular interactions, and develop active learning protocols for fine-tuning GPPs for molecular materials.
How has your research benefitted from using Bede?
Running Machine Learning Interatomic Potential Simulations on GPU Machine learning interatomic potential (MLIP) simulations are revolutionizing molecular modeling in chemistry and materials science. We are actively developing, testing, and discovering new scientific insights using a state-of-the-art software package called MACE. These simulations are computationally intensive and benefit greatly from GPU acceleration. However, access to GPU resources in the UK is extremely limited, and the Bede supercomputer has been an invaluable and irreplaceable resource for our work.
Has using Bede meant you were able to apply for further research funding?
Using Bede has allowed me to apply for further research funding. Access to GPU resources has enabled rapid prototyping and pilot studies, which are essential for developing competitive proposals. In particular, it has helped me advance new ideas in MLIP for modeling ion transport and excited-state chemistry, laying the groundwork for future grant applications.
