@Article{icces.2023.09761,
AUTHOR = {Jian Wang, Yonggang Zheng, Hongwu Zhang, Hongfei Ye},
TITLE = {A Four-Site Water Model for Liquid and Supercooled Water Based on  Machine Learning: TIP4P-BGWT},
JOURNAL = {The International Conference on Computational \& Experimental Engineering and Sciences},
VOLUME = {27},
YEAR = {2023},
NUMBER = {3},
PAGES = {1--1},
URL = {http://www.techscience.com/icces/v27n3/55170},
ISSN = {1933-2815},
ABSTRACT = {Water is the most ubiquitous fluid in nature and widely exists in the micro/nanoconfinement of leafstalks, 
shale, bones, etc. The complex relation of the properties and behaviours of water to the temperature, 
pressure and confinement size enhances the difficulty in the accurate simulation, such as the supercooled 
state of pure water below the freezing point. As a powerful tool, molecular dynamics simulation is adequate 
for investigating the relevant properties and behaviours. However, accurately calculating the physical 
properties of liquid and supercooled water is quite challenging by molecular simulations owing to limited 
model parameters. Machine learning (ML) techniques and temperature-dependent parameters provide a 
path to efficiently reparametrize TIP4P model. Here, 7000 molecular dynamics (MD) samples for liquid and 
supercooled water from 253 K to 373 K are generated to train the back-propagation neural network with 
better generalization ability. This network could rapidly and accurately provide adequate data for genetic 
algorithm to reparametrize the molecular model without extra time-consuming molecular simulations. 
Based on the proposed optimized approach, a water model TIP4P-BGWT with temperature-dependent 
model parameters is established. It exhibits excellent predictive performance with comprehensive balance 
for the four crucial physical properties (density, vaporization enthalpy, self-diffusion coefficient and 
viscosity) of water. The corresponding mean absolute percentage error is 3.26%, which is lower than the 
existing water models. Furthermore, the calculated results of the temperature of maximum density, thermal 
expansion coefficient, isothermal compressibility, surface tension, radial distribution function and the 
average number of hydrogen bonds per molecule are also in good consistent with experiments. It is notable 
that the established water model exhibits excellent performance for the supercooled water. The present 
study offers an accurate numerical model of liquid and supercooled water for the molecular simulationbased researches on the nanoflow, nanodroplet and interfacial fluids, etc.},
DOI = {10.32604/icces.2023.09761}
}