Susceptibility risk assessment of oil and gas pipeline geological hazards in mountainous areas based on data-driven model

Abstract

Geological hazards are recognized as causing significant damage to oil and gas pipelines, often resulting in catastrophic loss of life and property and hindering societal progress. In this study, a data-driven evaluation model is developed by integrating the Information Value method (IVM) with a Back Propagation Neural Network (BPNN) to assess the susceptibility of geological hazards in mountainous oil and gas pipelines. The IVM is used to identify non-hazardous areas, optimizing sample selection and reducing training errors, while the BPNN is employed to determine the weights of evaluation indicators, enhancing accuracy. First, an evaluation index system is proposed that comprehensively considers the natural geographical conditions and main disaster types. Next, non-disaster areas are located using the IVM and combined with disaster-prone areas to form the sample data. The sample data is then input into a BPNN for training, and the weights of each evaluation index are obtained from the trained network. Finally, a susceptibility risk assessment model is developed based on the derived weights and information values to accurately evaluate the susceptibility of pipeline geological hazards. A pipeline in China's Zhejiang Province's mountainous region is used as an illustration. Compared to the single IVM model and the single BPNN model, the receiver operator characteristic curve shows that the proposed method achieves significant improvements in the area under the curve by 9.8 % and 11.2 %, respectively, indicating a high level of evaluation accuracy. This study provides a reliable approach for assessing geological hazard susceptibility, offering scientific support for pipeline planning and hazard mitigation in oil and gas operations.