Integrated well-log data and seismic inversion results for prediction of hydrocarbon source rock distribution in W segment, Pearl River Mouth Basin, China

Hydrocarbon source rocks possess a high concentration of organic matter and can generate significant quantities of hydrocarbons, which are integral components within hydrocarbon systems. It is critical for well deployment and hydrocarbon production enhancement to accurately anticipate the geographical dispersion of hydrocarbon source rocks in hydrocarbon-bearing basins. Total Organic Carbon (TOC) serves as a pivotal metric for assessing hydrocarbon source rocks, enabling the estimation of their spatial distribution through TOC prediction. In this study, we present a Machine Learning-based process for predicting the distribution of hydrocarbon source rocks, utilizing well-log data and seismic inversion results. Based on the TOC value of the well curve, the hydrocarbon source rock quality is divided into four categories: normal, medium, good, and excellent. We identify the sensitive parameters governing hydrocarbon source rock quality through cross-plot and correlation analysis. Machine Learning will predict the spatial distribution of hydrocarbon source rock by establishing a relationship between hydrocarbon source rock quality and sensitive parameters. The prediction results are evaluated by comparing the performance of Random Forest, Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting tree (XGBoost), and Histogram-Based Gradient Boosting Decision Tree (HGBDT) using confusion matrix and ROC curve. The findings consistently demonstrate that HGBDT exhibits superior prediction capability, accurately anticipating the spatial distribution of hydrocarbon source rocks. The prediction outcomes align well with the depositional properties of the research area and demonstrate excellent agreement with the well data.