Abstract
• This work proposed a deep encoder-decoder neural network (DEDNN) for predicting TOC contents. • The DEDNN model shows more accurate and sensitive than ΔLogR method and CNN method. • The DEDNN model can highlight the contribution of individual logging curve to the TOC prediction. Total organic carbon (TOC) content is an important geochemical parameter for evaluating the hydrocarbon generation potential of unconventional oil and gas resources. The TOC content of source rocks significantly affects the responses of well logs so, in principle, well logs can be used for source rock appraisal. However, the complex relationships between TOC content and well logs involve nonlinear mapping with many parameters. It is sometimes difficult to obtain continuous and accurate TOC content values using conventional methods such as the ΔLogR method. In this study, we propose a TOC prediction model using a deep encoder-decoder neural network (DEDNN) based on mining and mapping of multiscale features of logging curves. The prediction performance of the model is validated by a series of tests using data from four exploration wells in the Longmaxi black shale in the Dingshan area of the Sichuan Basin. The TOC content prediction results confirm that the proposed DEDNN is more accurate than either the ΔLogR method or CNN, which is a state-of-the-art convolutional neural network. Furthermore, a saliency map derived from the DEDNN results shows the relative importance of different well logs to TOC contents.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.