In this study, universal and precise predictive models for CO2 frosting temperature in different natural gas mixtures were developed employing the machine learning algorithms of multilayer perceptron (MLP) and gaussian process regression (GPR). The models were verified by an extensive databank including 430 experimental samples collected from 7 published sources, enveloping a broad range of conditions in methane/CO2 binary mixtures as well as the ternary mixtures of methane/CO2/ethane and methane/CO2/nitrogen. Both GPR and MLP models exhibited excellent predictions with total average absolute relative errors (AAREs) of 0.16% and 0.42%, and R2 values of 99.80% and 99.38%, respectively. The novel models use only 4 simple adjusted parameters, and they were found to be applicable for both binary and ternary mixtures with high precisions. In addition, the effects of each operating parameter on frosting temperature were studied, and the new models showed excellent physical trends. Subsequently, in order to provide more insight about the most effective factors on frosting temperature, a sensitivity analysis based on the present databank was performed.
