The most basic carbon-based molecules are hydrocarbons which sizes differ considerably, impacting thermodynamic, transport, optical, and interfacial characteristics such as heat capacity, enthalpy, thermal expansion, sound speed, critical phenomena, dielectric constant, refractive index, emissivity, reflectivity, transmissivity, absorptivity, viscosity, thermal and electrical conductivity, mass diffusivity; thermal diffusivity, and effusivity. Petroleum and natural gas are mostly made up of hydrocarbons that are used as fuels and lubricants, as well as raw materials for plastics, rubber, solvents, and industrial chemicals. Aliphatic compounds are hydrocarbons that are open-chain compounds and closed chains. On the other hand, non-hydrocarbons components like acid gases, such as hydrogen sulfide and carbon dioxide; inert gases, such as nitrogen and helium; odorous sulfurous gases, such as hydrogen sulfide and various mercaptans; and other impurities, such as water and mercury vapors and sulfur dissolved in gas, are the most common non-hydrocarbon components.

There are different ways to determine the values of the properties of both hydrocarbon and non-hydrocarbon components; from experimental methods which are time-consuming to the using of correlations like the equation of state (EOS) and most recently the application and design of different models using artificial intelligence (AI), machine learning (ML) that use computational modeling as a means of achieving precise and reliable results with higher accuracy and speed.

This Special Issue aims to collate original research and review papers describing advances in determining, evolving, evaluating, optimizing, and predicting the properties of hydrocarbon and non-hydrocarbon systems using machine learning and artificial intelligence techniques. Submissions focusing on the application of intelligence methods in these fields related to the petroleum and chemical engineering sciences through experimental methods or data analysis approaches are particularly encouraged.

Potential topics include but are not limited to the following:

• Thermodynamic, electronic, transport, thermal, and physical properties of hydrocarbons and non-hydrocarbons
• Optimization and prediction of natural gas properties of pure and mixed hydrocarbons
• Data mining applications in the oil and gas industry
• Intelligent control of greenhouse gas emissions and capture
• Application of machine learning in hydrocarbon and non-hydrocarbon systems
• Estimating the absorption, solubility, and properties of major air pollutant gasses
• Prediction of diffusivities in supercritical gas systems
• Application of EOS and machine learning approaches in electrolyte and non-electrolyte solutions
• Estimating biogas and biofuel properties by soft computing and intelligent models
• Modeling the equilibrium of two and three-phase systems containing hydrocarbons and non-hydrocarbons
• Application of artificial intelligence for gas-based enhanced oil recovery
• Prediction of natural gas consumption by applying connectionist approaches
• Modeling of natural gas hydrate formation using computational schemes
• Assessment of water quality parameters using intelligent approaches
• Application of QSPR and QSAR modeling in CO2 capture technology