Improved reliability and availability of fundamental properties for all hydrogen isotopologues by Gaussian process regression using data from experiments and path-integral simulations

Abstract

The thermodynamic and transport properties of hydrogen isotopologues in the solid, liquid, and gas phases are crucial for hydrogen energy exploitation, such as the design of the fuel cycle of nuclear fusion reactors. However, experimental data for tritium-containing species are often not available. Alternatively, path integral (PI) simulation can evaluate hydrogen properties taking into account nuclear quantum effects; however, concerns about its reliability are present. This study proposes a method of Gaussian process regression (GPR) using both experimental and PI simulation data to obtain practically plausible estimates for all isotopologues. Using liquid viscosity and diffusivity as test cases, we demonstrate that the present method has high and robust predictive performance. The method has broad applicability and can also be used to design experiments and calculations to efficiently improve the regression model, and thus is expected to contribute to enhancing the availability and reliability of the hydrogen isotopologue property database.