Hierarchical Surrogate-Assisted Evolutionary Algorithm for Integrated Multi-Objective Optimization of Well Placement and Hydraulic Fracture Parameters in Unconventional Shale Gas Reservoir

Integrated optimization of well placement and hydraulic fracture parameters in naturally fractured shale gas reservoirs is significance to enhance unconventional hydrocarbon energy resources the oil industry. However, task usually presents intensive computation-cost due numerous high-fidelity model simulations, particularly for field-scale application. We present an efficient multi-objective framework supported by a novel hierarchical surrogate-assisted evolutionary algorithm multi-fidelity modeling technology. In proposed framework, both net value (NPV) cumulative production (CGP) are regarded as bi-objective functions that need be optimized. The employs particle-swarm global–local hybridization searching strategy where low-fidelity surrogate capable exploring populations globally, while models update current thus generate next generations locally. multi-layer perception chosen this study. performance our global approach verified optimize on hydraulically reservoir. can obtain NPV CPG with satisfactory accuracy only 500 training samples. significantly contributes convergent algorithm.