Abstract
Current study results on Machine Learning have been published. According to news reporting originating from Telangana, India, by NewsRx correspondents, research stated, “In this study, we have trained and compared five regression machine learning (ML) algorithms to assess their predictive capabilities in reproducing thermodynamic and transport properties of alkanes as well as refrigerants. We also examined the pairwise correlation between the input features, which consisted of molecular structural details for alkanes and the number of different atoms for refrigerants, and various thermophysical properties.” Financial support for this research came from Science and Engineering Research Board , India. Our news editors obtained a quote from the research from the National Institute of Technology Warangal, “The ML models used for prediction include random forest regression, decision tree regression, feedforward neural network, multiple linear regression, and polynomial regression. These models were trained to predict thermophysical properties such as kinematic viscosity, speed of sound, molar heat capacity, thermal conductivity, and enthalpy at various temperatures and pressures. Among the tested models, the random forest regression model demonstrated superior predictive capabilities compared to the other four models in terms of coefficient of determination (R2), average absolute relative deviation (%AARD) and mean absolute error (MAE) for the examined alkanes and refrigerants. We can conclude that the trained ML models can be utilized to predict thermophysical properties of alkanes and refrigerants accurately and quickly. Upon analysing the pairwise correlation coefficient matrix, it was evident that certain molecular features had a strong influence on individual thermophysical properties of alkanes as well as refrigerants.”
NETL
NSTL
Elsevier