August 15, 2025ProcessesOpen Access

An Improved XGBoost Model for Development Parameter Optimization and Production Forecasting in CO2 Water-Alternating-Gas Processes: A Case Study of Low Permeability Reservoirs in China

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Predictive model improves parameter optimization and forecasting in CO2 water-alternating-gas processes, indicating robust performance.

The study reveals a new model that achieves a coefficient of determination of 0.9894 in CO2-WAG injection predictions, showcasing its high accuracy.
Experimental validation includes 1225 multivariable simulations, with results consistently showing errors within ±2%, confirming the model’s reliability.
Advanced hyperparameter tuning methods, including Chebyshev chaotic mapping, enhance the model’s performance for complex low-permeability reservoir studies.
The ICPO-XGBoost model highlights its superior generalization capabilities, proving to be a promising tool for effective reservoir management.

Su et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark