Permeability prediction using logging data from tight reservoirs based on deep neural networks

• Published in: Journal of applied geophysics Vol. 229; p. 105501
• Main Authors: Fang, Zhijian, Ba, Jing, Carcione, José M., Xiong, Fansheng, Gao, Li
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2024
• Subjects: Deep neural networks; Machine learning; Ordos Basin; Permeability prediction; Tight reservoirs; Well-log data; Ordos Basin; Deep neural networks; Permeability prediction; Tight reservoirs; Well-log data; Machine learning
• ISSN: 0926-9851
• DOI: 10.1016/j.jappgeo.2024.105501

Permeability is a critical parameter for evaluating reservoir properties, and accurate prediction is an important basis for identifying high-quality reservoirs and geological modeling. However, the strong heterogeneity, complex lithology and diagenesis in the reservoirs of this region pose a major challenge for the accurate assessment of reservoir permeability. In recent years, the use of machine learning (ML) to solve problems in geophysical well logging and related fields has gained much attention thanks to advances in data science and artificial intelligence. ML is any predictive algorithm or combination of algorithms that learns from data and makes predictions without being explicitly coded with a deterministic model. The most immediate example is deep neural networks (DNN) that are trained with data to minimize a cost function and make predictions. The tight reservoirs in the Chang 7 Member of the Ordos Basin host significant oil and gas resources and have recently emerged as the main focus of unconventional oil and gas exploration and development. In this work, we performed DNN-based permeability prediction for the tight reservoirs in the Ordos Basin area. From 19 well logs, we selected effective data points from 17 wells for DNN training after preprocessing and used the remaining two wells for testing. First, we trained the DNN with all collected parameters as inputs, resulting in permeability prediction R2 values of 0.64 and 0.72 for the two wells, indicating a good fit. We then optimized the input parameters by performing a crossplot analysis between these parameters and the permeability. Using the same network structure (with all hyperparameters set the same), we trained the DNN again to obtain a new DNN-based model. The prediction results showed that removing input parameters with poor correlation to permeability improved the prediction accuracy with R2 values of 0.70 and 0.87 for the two wells. •DNN-based method is developed to predict permeability by using logging data of tight reservoirs.•Optimizing the input parameters by performing a crossplot analysis between input parameters and the permeability to improve prediction accuracy.•The proposed method achieves satisfactory results in the practical applications for tight reservoirs.