Deep Learning for Predicting Hydrogen Solubility in n-Alkanes: Enhancing Sustainable Energy Systems

Abstract

As global population growth and urbanisation intensify energy demands, the quest for sustainable energy sources gains paramount importance. Hydrogen (H2) emerges as a versatile energy carrier, contributing to diverse processes in energy systems, industrial applications, and scientific research. To harness the H2 potential effectively, a profound grasp of its thermodynamic properties across varied conditions is essential. While field and laboratory measurements offer accuracy, they are resource-intensive. Experimentation involving high-pressure and high-temperature conditions poses risks, rendering precise H2 solubility determination crucial. This study evaluates the application of Deep Neural Networks (DNNs) for predicting H2 solubility in n-alkanes. Three DNNs are developed, focusing on model structure and overfitting mitigation. The investigation utilises a comprehensive dataset, employing distinct model structures. Our study successfully demonstrates that the incorporation of dropout layers and batch normalisation within DNNs significantly mitigates overfitting, resulting in robust and accurate predictions of H2 solubility in n-alkanes. The DNN models developed not only perform comparably to traditional ensemble methods but also offer greater stability across varying training conditions. These advancements are crucial for the safe and efficient design of H2-based systems, contributing directly to cleaner energy technologies. Understanding H2 solubility in hydrocarbons can enhance the efficiency of H2 storage and transportation, facilitating its integration into existing energy systems. This advancement supports the development of cleaner fuels and improves the overall sustainability of energy production, ultimately contributing to a reduction in reliance on fossil fuels and minimising the environmental impact of energy generation.