Identification of Karst Cavities from 2D Seismic Wave Impedance Images Based on Gradient-Boosting Decision Trees Algorithms (GBDT): Case of Ordovician Fracture-Vuggy Carbonate Reservoir, Tahe Oilfield, Tarim Basin, China

• Published in: Energies (Basel) Vol. 16; no. 2; p. 643
• Main Authors: Kouassi, Allou Koffi Franck, Pan, Lin, Wang, Xiao, Wang, Zhangheng, Mulashani, Alvin K., James, Faulo, Shaame, Mbarouk, Hussain, Altaf, Hussain, Hadi, Nyakilla, Edwin E.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Accuracy; Algorithms; Caves; Classification; Datasets; Decision trees; Enhanced oil recovery; fracture-vuggy carbonate reservoir; Geology; gradient-boosting decision trees (GBDT); Hydrocarbons; karst cavities; Machine learning; Neural networks; Reservoirs; Software; Tahe oilfield; uncertainty; Visual Geometry Group 16 pre-trained (VGG-16); China; Tarim Basin

The precise characterization of geological bodies in fracture-vuggy carbonates is challenging due to their high complexity and heterogeneous distribution. This study aims to present the hybrid of Visual Geometry Group 16 (VGG-16) pre-trained by Gradient-Boosting Decision Tree (GBDT) models as a nove...