Web development of a machine learning tool that automatically determines the origin of natural gas with increased accuracy and confidence over the current methods

Abstract

Previous methods to determine the origin of natural gases consist mostly of analyzing combinations of three empirical binary plots with molecular ratio C1/(C2+C3) and isotopic values δ13C-C1, δ12H-C1, and δ13C-CO2. Using these diagrams, geochemists distinguish five origins of natural gas: abiotic, thermogenic, primary microbial from CO2 reduction primary microbial from methyl-type fermentation and secondary microbial. However, the genetic fields on these diagrams partially overlap, making the interpretation of some samples ambiguous. Here, I integrate supervised machine learning to improve these methods and create a tool that dramatically increases the accuracy, certainty and speed of classifying a natural gas sample. With data science and software engineering, I utilized a dataset of 27,853 natural gas samples to create and deploy a random forest natural gas classifier tool that uses the same geochemical parameters as the binary diagrams. This web tool that can automatically classify the origin of natural gas at an accuracy of over 97% and provide calculated certainty of each classification.