TOC prediction using a gradient boosting decision tree method: A case study of shale reservoirs in Qinshui Basin

Abstract

Shale oil and shale gas are important unconventional resources. As the total organic carbon (TOC) of shales is related to the generation potentiality of hydrocarbons, accurate TOC prediction models can improve development efficiency and reduce cost. However, there has been little work on intelligent prediction of TOC. This study focused on hydrocarbon-rich shale from the Linfen area of Qinshui Basin in China. Multiple regression analysis (MRA), ΔlgR, back propagation (BP) neural network, gradient boosting decision tree (GBDT) were selected to predict the TOC of the studied shale reservoirs using density (DEN), uranium (U), acoustic (AC), and resistivity (RT) logs. The predicted TOC was compared with the geochemical-measured TOC. To fairly evaluate these models, the correlation of determination (R2), root-mean-square-error (RMSE) and three-scale analytic hierarchy process (TAHP) were introduced. The results show that MRA, ΔlgR, and BP methods gave low R2, high RMSE values, and low total weight, indicating these methods poorly predicted TOC. These models significantly underestimate the TOC, resulting in evident deviations between the predicted TOC and their real values. In contrast, GBDT provided accurate TOC prediction, with values of R2, RMSE, and total weight of 0.9254, 0.032 and 0.42. The GBDT model can greatly outperform other models by extracting complex relationships between well log data and TOC values. Sensitivity analysis of the GBDT model revealed that the U parameter exhibited the greatest impact on TOC prediction. The results of this work show that the GBDT model is well suited for TOC prediction of unconventional resources.