Explainable machine learning for sandstone rock typing: Triple-anchor convergence with closed-form permeability laws

Traditional rock typing in reservoir engineering relies on destructive, costly, and slow macroscopic core measurements. We propose an explainable machine-learning framework, of which the central contribution is a triple-anchor cross-paradigm audit that confronts the supervised model’s SHAP attributi...

Descrición completa

Detalles Bibliográficos

Principais autores:	Irwan Ary Dharmawan, Safira Rahma Kartika, Aldenia Alexandra, Benedicta Loveni Melkisedek, Yoevita Emeliana
Formato:	Artigo
Idioma:	Inglês
Publicado:	Elsevier 2026-08-01
Series:	Chemical Engineering Journal Advances
Assuntos:	Explainable machine learning Sandstone rock typing Pore-network topology Kozeny–Carman permeability Spatial-block cross-validation
Acceso en liña:	http://www.sciencedirect.com/science/article/pii/S2666821126002917
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!