Permeability Predictions for Tight Sandstone Reservoir Using Explainable Machine Learning and Particle Swarm Optimization

• Published in: Geofluids Vol. 2022; pp. 1 - 15
• Main Authors: Liu, Jing-Jing, Liu, Jian-Chao
• Format: Journal Article
• Language: English
• Published: Chichester Hindawi 06.01.2022; John Wiley & Sons, Inc; Wiley
• Subjects: Accuracy; Additives; Algorithms; Analysis; Artificial intelligence; Datasets; Decision trees; Deep learning; Electrical resistivity; Experiments; Gamma rays; Learning algorithms; Logging; Machine learning; Mathematical models; Mathematical optimization; Methods; Natural gas reserves; Oil reserves; Optimization; Particle swarm optimization; Permeability; Porosity; Predictions; Regression analysis; Regression models; Reservoirs; Robustness (mathematics); Sandstone; Sedimentary rocks; Shale; Slopes; Support vector machines; China; Ordos Basin

High-precision permeability prediction is of great significance to tight sandstone reservoirs. However, while considerable progress has recently been made in the machine learning based prediction of reservoir permeability, the generalization of this approach is limited by weak interpretability. Henc...