Intelligent geochemical interpretation of mass chromatograms: Based on convolution neural network

Abstract

Gas chromatography-mass spectrometry (GC-MS) is an extremely important analytical technique that is widely used in organic geochemistry. It is the only approach to capture biomarker features of organic matter and provides the key evidence for oil-source correlation and thermal maturity determination. However, the conventional way of processing and interpreting the mass chromatogram is both time-consuming and labor-intensive, which increases the research cost and restrains extensive applications of this method. To overcome this limitation, a correlation model is developed based on the convolution neural network (CNN) to link the mass chromatogram and biomarker features of samples from the Triassic Yanchang Formation, Ordos Basin, China. In this way, the mass chromatogram can be automatically interpreted. This research first performs dimensionality reduction for 15 biomarker parameters via the factor analysis and then quantifies the biomarker features using two indexes (i.e. MI and PMI) that represent the organic matter thermal maturity and parent material type, respectively. Subsequently, training, interpretation, and validation are performed multiple times using different CNN models to optimize the model structure and hyper-parameter setting, with the mass chromatogram used as the input and the obtained MI and PMI values for supervision (label). The optimized model presents high accuracy in automatically interpreting the mass chromatogram, with R2 values typically above 0.85 and 0.80 for the thermal maturity and parent material interpretation results, respectively. The significance of this research is twofold: (i) developing an efficient technique for geochemical research; (ii) more importantly, demonstrating the potential of artificial intelligence in organic geochemistry and providing vital references for future related studies.