Investigation of the fracture initiation pressure for water injection wells in poorly consolidated sandstone reservoir

Simulation and Prediction of Injection Pressure in CO2 Geological Sequestration Based on Improved LSO Algorithm and BP Neural Networks

“…The LSO algorithm was improved to optimize the structure of the BPNN by combining the chaotic tent mapping with the DE mechanism to address the problems of slow convergence of the BPNN and its tendency to fall into local optimal solutions. Experimental results show that the ILSO_BP model achieves better performance in the comprehensive evaluation of the maximum injection pressure for CO 2 geological storage, and the 18 Geofluids convergence speed and prediction accuracy are higher than those of other three methods. Thus, the method proposed in this work can provide useful guidance for the injection management of geological CO 2 storage projects, improve safety and storage efficiency, and reduce the risk of gas leakage.…”

“…In addition, the mechanical and permeability properties of reservoir caprock are obtained from the core test data, and porosity and permeability, as important parameters affecting the sequestration performance, present a complex multiparameter, nonlinear mapping relationship with the maximum injection pressure [17]. However, the measurement and sampling errors and the complexity of the geological environment lead to the incompleteness and some uncertainty in the logging data [18,19]. The mean value of the formation parameters in the field is generally used in the model calculation, which leads to the deviations between the calculated results and the actual geological conditions.…”