scholarly journals DIFFUSION MONTE CARLO USING MACHINE LEARNING POTENTIAL ENERGY SURFACES

2021 ◽  
Author(s):  
Ryan DiRisio ◽  
Anne McCoy ◽  
Fenris Lu ◽  
Jacob Finney ◽  
Mark Boyer
Keyword(s):  
Machine Learning ◽  
Monte Carlo ◽  
Potential Energy ◽  
Potential Energy Surfaces ◽  
Learning Potential ◽  
Diffusion Monte Carlo ◽  
Energy Surfaces

scholarly journals Choosing the right molecular machine learning potential

2021 ◽  
Author(s):  
Max Pinheiro Jr ◽  
Fuchun Ge ◽  
Nicolas Ferré ◽  
Pavlo O. Dral ◽  
Mario Barbatti
Keyword(s):  
Machine Learning ◽  
Potential Energy ◽  
Quantum Chemistry ◽  
Potential Energy Surfaces ◽  
Reaction Rates ◽  
Learning Potential ◽  
Physicochemical Processes ◽  
The Right ◽  
Energy Surfaces ◽  
Insight Into

Quantum-chemistry simulations based on potential energy surfaces of molecules provide invaluable insight into the physicochemical processes at the atomistic level and yield such important observables as reaction rates and spectra....

Monte Carlo studies of aqueous solution of nitrogen using different potential energy surfaces

1986 ◽  
Vol 58 (1) ◽  
pp. 65-83 ◽  
Author(s):  
E.S. Fois ◽  
A. Gamba ◽  
G. Morosi ◽  
P. Demontis ◽  
G.B. Suffritti
Keyword(s):  
Aqueous Solution ◽  
Monte Carlo ◽  
Potential Energy ◽  
Potential Energy Surfaces ◽  
Monte Carlo Studies ◽  
Energy Surfaces

scholarly journals Easy representation of multivariate functions with low-dimensional terms via Gaussian process regression kernel design: applications to machine learning of potential energy surfaces and kinetic energy densities from sparse data

2022 ◽  
Author(s):  
Sergei Manzhos ◽  
Eita Sasaki ◽  
Manabu Ihara
Keyword(s):  
Machine Learning ◽  
Kinetic Energy ◽  
Potential Energy ◽  
Gaussian Process ◽  
Potential Energy Surfaces ◽  
Gaussian Process Regression ◽  
Multivariate Functions ◽  
Low Dimensional ◽  
Energy Surfaces ◽  
Kernel Design

Abstract We show that Gaussian process regression (GPR) allows representing multivariate functions with low-dimensional terms via kernel design. When using a kernel built with HDMR (High-dimensional model representation), one obtains a similar type of representation as the previously proposed HDMR-GPR scheme while being faster and simpler to use. We tested the approach on cases where highly accurate machine learning is required from sparse data by fitting potential energy surfaces and kinetic energy densities.

Sign in / Sign up

Export Citation Format

Share Document