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
Authors:
- Allou Koffi Franck KouassiAKAllou Koffi Franck Kouassi
- Lin PanLPLin Pan
- Xiao WangXWXiao Wang
- Zhangheng WangZWZhangheng Wang
- Alvin K. MulashaniAMAlvin K. Mulashani
- Faulo JamesFJFaulo James
- Mbarouk ShaameMSMbarouk Shaame
- Altaf HussainAHAltaf Hussain
- Hadi HussainHHHadi Hussain
- Edwin E. NyakillaENEdwin E. Nyakilla
Open Access
Abstract
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 novel approach for predicting and generating karst cavities with high accuracy on various scales based on uncertainty assessment from a small dataset. Seismic wave impedance images were used as input data. Their manual interpretation was used to build GBDT classifiers for Light Gradient-Boosting Machine (LightGBM) and Unbiased Boosting with Categorical Features (CatBoost) for predicting the karst cavities and unconformities. The results show that the LightGBM was the best GBDT classifier, which performed excellently in karst cavity interpretation, giving an F1-score between 0.87 and 0.94 and a micro-G-Mean ranging from 0.92 to 0.96. Furthermore, the LightGBM performed better in cave prediction than Linear Regression (LR) and Multilayer Perceptron (MLP). The prediction of karst cavities according to the LightGBM model was performed well according to the uncertainty quantification. Therefore, the hybrid VGG16 and GBDT algorithms can be implemented as an improved approach for efficiently identifying geological features within similar reservoirs worldwide.Keywords
This publication has 75 references indexed in Scilit:
- Application of multi-seismic attributes analysis in the study of distributary channelsMarine and Petroleum Geology, 2016
- Multi-layered ordovician paleokarst reservoir detection and spatial delineation: A case study in the Tahe Oilfield, Tarim Basin, Western ChinaMarine and Petroleum Geology, 2016
- A reserve calculation method for fracture-cavity carbonate reservoirs in Tarim Basin, NW ChinaPetroleum Exploration and Development, 2015
- Prediction of buried calcite dissolution in the Ordovician carbonate reservoir of the Tahe Oilfield, NW china: Evidence from formation waterGeochemistry, 2013
- The Early Hercynian paleo-karstification in the Block 12 of Tahe oilfield, northern Tarim Basin, ChinaCarbonates and Evaporites, 2013
- Features and controlling factors of epigenic karstification of the Ordovician carbonates in Akekule arch, Tarim BasinJournal of Earth Science, 2012
- Advances in carbonate exploration and reservoir analysisGeological Society, London, Special Publications, 2012
- Fractured reservoir modeling by discrete fracture network and seismic modeling in the Tarim Basin, ChinaPetroleum Science, 2011
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997