XGBoost algorithm applied in the interpretation of tight-sand gas reservoir on well logging data

被引：0

作者：

Yan X. ^{[1
]}

Gu H. ^{[1
,2
]}

Xiao Y. ^{[1
]}

Ren H. ^{[1
]}

Ni J. ^{[1
]}

机构：

[1] Institute of Geophysics and Geomatics, China University of Geosciences(Wuhan), Wuhan, 430074, Hubei

[2] Hubei Subsurface Multi-scale Imaging Key Laboratory, Wuhan, 430074, Hubei

来源：

Shiyou Diqiu Wuli Kantan/Oil Geophysical Prospecting | 2019年 / 54卷 / 02期

关键词：

Machine learning; Tight-sand gas reservoir; Well logging data interpretation; XGBoost algorithm;

D O I：

10.13810/j.cnki.issn.1000-7210.2019.02.024

中图分类号：

学科分类号：

摘要：

Conventional single-model machine learning methods used in tight-sand gas reservoir interpretation on well logging data have the multi-solution problem. To overcome this problem, we use the XGBoost algorithm. Based on logging data in the Area A, different types of well logging data are used as input variables, and a regression prediction model is established by XGBoost algorithm. The porosity and permeability in this area are predicted. The optimization of various parameters in XGBoost algorithm is also discussed. The classification prediction model established by XGBoost algorithm predicts reservoir types in the area. Based on our prediction results, the XGBoost algorithm achieves a better porosity & permeability prediction and tight-sand gas reservoir identification in the area compared with the random forest method and vector-supported machine algorithms. © 2019, Editorial Department OIL GEOPHYSICAL PROSPECTING. All right reserved.

引用

页码：447 / 455

页数：8

共 25 条

[1] Luo R., Lei Q., Fan J., Et al., A new approach to the dynamic reserve estimation of fractured gas wells in low-permeability tight gas reservoirs: The Sulige Gas Field as a case study, Natural Gas Industry, 30, 7, pp. 28-31, (2010)
[2] Zhao Y., Wu C., Wu D., Logging evaluation to tight gas sandstone: a case study from the first member of Shanxi formation in Daniudi gas pool, Ordos basin, China, Geological Science and Technology Information, 22, 4, pp. 65-70, (2003)
[3] Yang S., New methods of Log Evaluation of the Tight Sandstone Gas Reservoirs in E'erduosi Basin, Natural Gas Industry, 25, 9, pp. 45-47, (2005)
[4] Wei Q., Xiao L., Li K., Identify gas potential in tight reservoir by conventional logging, Special Oil and Gas Reservoirs, 14, 4, pp. 22-25, (2007)
[5] Zhang X., Pan H., Luo M., Et al., Summary of logging interpretation for gas-bearing tight sandstone, Chinese Journal of Engineering Geophysics, 2, 6, pp. 431-436, (2005)
[6] Rogers S.J., Fang J.H., Karr C.L., Et al., Determination of lithology from well logs using a neural network, AAPG Bulletin, 76, 5, pp. 731-739, (1992)
[7] Baldwin J.L., Bateman R.M., Wheatley C.L., Application of a neural network to the problem of mineral identification from well logs, Log Analyst, 3, 5, pp. 279-293, (1990)
[8] Zhang X., Zhang Y., Reservoir prediction through cross-validation based on support vector machine, Geophysical Prospecting for Petroleum, 57, 4, pp. 597-600, (2018)
[9] Anazi A., Gates I.D., On the capability of support vector machines to classify lithology from well logs, Natural Resources Research, 19, 2, pp. 125-139, (2010)
[10] Sebtosheikh M.A., Motafakkerfard R., Riahi M.A., Et al., Support vector machine method, a new technique for lithology prediction in an Iranian heterogeneous carbonate reservoir using petrophysical well logs, Carbonates Evaporites, 30, 1, pp. 59-68, (2015)

← 1 2 3 →