Fracturing risks such as casing deformation and frac hits occur frequently during the fracturing process of deep shale gas horizontal wells. These risks cause significant differences between the expected stimulation performance and the actual production. Therefore, it is necessary to evaluate the production enhancement potential of deep shale gas horizontal wells considering fracturing risk effects. A fracturing risk prediction model was developed using a back propagation neural network optimized by particle swarm optimization (BP-PSO). A hydraulic fracture propagation model was established based on rock mechanics and fracture mechanics. A post-fracturing productivity evaluation model was built based on advanced seepage mechanics theory. These models were integrated and combined with field data to establish a production enhancement potential evaluation method. Field application results show that the predicted high-risk stages of Well Y correspond well with the actual risk occurrences. The error between the predicted and actual EUR per kilometer is 13.1%, verifying the reliability of the proposed method. The research results enable the prediction of production enhancement potential under fracturing risk effects. They also provide a solid theoretical basis for the economic feasibility analysis of fracturing operations.
Wang et al. (2026) studied this question.