NMR-data-driven prediction of matrix permeability in sandstone aquifers

•Matrix k was accurately predicted by machine learning models from the NMR T2 data.•The cumulative T2 data as inputs provided higher accuracy for k than original bins.•The optimal GBDT model was visualized and interpreted by the game-theory SHAP method.•The classical SDR and Timur-Coates models unde...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of hydrology (Amsterdam) 2023-03, Vol.618, p.129147, Article 129147
Hauptverfasser:	Chen, Xiaojun, Zhao, Xiaobo, Tahmasebi, Pejman, Luo, Chengfei, Cai, Jianchao
Format:	Artikel
Sprache:	eng
Schlagworte:	bedrock Data-driven decision support systems hydrology Machine learning Matrix permeability Nuclear magnetic resonance nuclear magnetic resonance spectroscopy permeability prediction sandstone Sandstone aquifer T2 spectrum
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!