Projects per year
Abstract
We present a comprehensive methodology to enable the addition of van der Waals (vdW) corrections to machine learning (ML) atomistic force fields. Using a Gaussian approximation potential (GAP) [Bartók et al., Phys. Rev. Lett. 104, 136403 (2010)10.1103/PhysRevLett.104.136403] as a baseline, we accurately machine learn a local model of atomic polarizabilities based on Hirshfeld volume partitioning of the charge density [Tkatchenko and Scheffler, Phys. Rev. Lett. 102, 073005 (2009)10.1103/PhysRevLett.102.073005]. These environmentdependent polarizabilities are then used to parametrize a screened Londondispersion approximation to the vdW interactions. Our ML vdW model only needs to learn the charge density partitioning implicitly by learning the reference Hirshfeld volumes from density functional theory (DFT). In practice, we can predict accurate Hirshfeld volumes from the knowledge of the local atomic environment (atomic positions) alone, making the model highly computationally efficient. For additional efficiency, our ML model of atomic polarizabilities reuses the same manybody atomic descriptors used for the underlying GAP learning of bonded interatomic interactions. We also show how the method enables straightforward computation of gradients of the observables, even when these remain challenging for the reference method (e.g., calculating gradients of the Hirshfeld volumes in DFT). Finally, we demonstrate the approach by studying the phase diagram of C60, where vdW effects are important. The need for a highly accurate vdWinclusive reactive force field is highlighted by modeling the decomposition of the C60 molecules taking place at high pressures and temperatures.
Original language  English 

Article number  054106 
Number of pages  16 
Journal  Physical Review B 
Volume  104 
Issue number  5 
DOIs  
Publication status  Published  6 Aug 2021 
MoE publication type  A1 Journal articlerefereed 
Fingerprint
Dive into the research topics of 'Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C60'. Together they form a unique fingerprint.Datasets

GAP interatomic potential for C60
Muhli, H. (Contributor) & Caro Bayo, M. (Contributor), 2021
DOI: 10.5281/zenodo.4616343, https://zenodo.org/record/4616343
Dataset

NEXTCELL: Nextgeneration interatomic potentials to simulate new cellulosebased materials (NEXTCELL)
01/09/2020 → 31/08/2025
Project: Academy of Finland: Other research funding

Formation of CO, CH4 and CH3OH by electrochemical reduction of CO2
Caro Bayo, M., Kuklin, M., Pršlja, P., Lehtomäki, J., Heinolainen, A., Hernandez Leon, P. & Kloppenburg, J.
01/01/2020 → 31/12/2023
Project: Academy of Finland: Other research funding

COMPEX: Towards accurate computational experimentation: machinelearningdriven simulation of nanocarbon synthesis
Caro Bayo, M., Jana, R., Muhli, H., Hernandez Leon, P., Kondati Natarajan, S., Heinolainen, A. & Zarrouk, T.
01/09/2019 → 31/08/2023
Project: Academy of Finland: Other research funding