Multi-Task Learning Network-Based Prediction of Hydraulic Fracturing Effects in Horizontal Wells Within the Ordos Yanchang Formation Tight Reservoir

• Published in: Processes 2024-10, Vol.12 (10), p.2279
• Main Authors: Fan, Pingtian, Yuan, Hai, Song, Xiankun, Yang, Xiaowen, Song, Zhenyu, Li, Ping, Lin, Ziyu, Gan, Maozong, Liu, Yuetian
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial intelligence; Construction; Correlation analysis; Efficiency; Finite element analysis; Finite volume method; Fractures (Geology); Geology; Horizontal wells; Hydraulic fracturing; Machine learning; Mathematical optimization; Morphology; Oil wells; Optimization; Particle swarm optimization; Permeability; Prediction models; Predictions; Productivity; Reservoirs; Simulation; Software; Thickness
• ISSN: 2227-9717; 2227-9717
• DOI: 10.3390/pr12102279

Accurate prediction of fracture volume and morphology in horizontal wells is essential for optimizing reservoir development. Traditional methods struggle to capture the intricate relationships between fracturing effects, geological variables, and operational factors, leading to reduced prediction accuracy. To address these limitations, this paper introduces a multi-task prediction model designed to forecast fracturing outcomes. The model is based on a comprehensive dataset derived from fracturing simulations within the Long 4 + 5 and Long 6 reservoirs, incorporating both operational and geological factors. Pearson correlation analysis was conducted to assess the relationships between these factors, ranking them according to their influence on fracturing performance. The results reveal that operational variables predominantly affect Stimulated Reservoir Volume (SRV), while geological variables exert a stronger influence on fracture morphology. Key operational parameters impacting fracturing performance include fracturing fluid volume, total fluid volume, pre-fluid volume, construction displacement, fracturing fluid viscosity, and sand ratio. Geological factors affecting fracture morphology include vertical stress, minimum horizontal principal stress, maximum horizontal principal stress, and layer thickness. A multi-task prediction model was developed using random forest (RF) and particle swarm optimization (PSO) methodologies. The model independently predicts SRV and fracture morphology, achieving an R2 value of 0.981 for fracture volume predictions, with an average error reduced to 1.644%. Additionally, the model’s fracture morphology classification accuracy reaches 93.36%, outperforming alternative models and demonstrating strong predictive capabilities. This model offers a valuable tool for improving the precision of fracturing effect predictions, making it a critical asset for reservoir development optimization.