Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model

Gu Yufeng; Zhang Daoyong; Bao Zhidong; Guo Haixiao; Zhou Liming; Ren Jihong

doi:10.19509/j.cnki.dzkq.2021.0416

Volume 40 Issue 4

Jul. 2021

Turn off MathJax

Article Contents

Article Navigation > Bulletin of Geological Science and Technology > 2021 > 40(4): 224-234

Gu Yufeng, Zhang Daoyong, Bao Zhidong, Guo Haixiao, Zhou Liming, Ren Jihong. Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model[J]. Bulletin of Geological Science and Technology, 2021, 40(4): 224-234. doi: 10.19509/j.cnki.dzkq.2021.0416

Citation:

Gu Yufeng, Zhang Daoyong, Bao Zhidong, Guo Haixiao, Zhou Liming, Ren Jihong. Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model[J]. Bulletin of Geological Science and Technology, 2021, 40(4): 224-234. doi: 10.19509/j.cnki.dzkq.2021.0416

Citation:

Gu Yufeng, Zhang Daoyong, Bao Zhidong, Guo Haixiao, Zhou Liming, Ren Jihong. Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model[J]. Bulletin of Geological Science and Technology, 2021, 40(4): 224-234. doi: 10.19509/j.cnki.dzkq.2021.0416

PDF( 2034 KB)

Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model

doi: 10.19509/j.cnki.dzkq.2021.0416

Received Date: 30 Nov 2020

Abstract

Abstract

Classic lithology predictors, represented by crossplot, are generally ineffective for tight sandstone formation, mainly due to a point that most lithologies present extremely similar logging responses and thus are rather difficult to be analyzed effectively via crossplot.Compared to classic pattern recognizers, LightGBM shows higher efficiency in data process, therefore it is employed to make a solution for lithology prediction of tight sandstone formation.As LightGBM utilizes many hyper-parameters during modeling, easily causing an issue that the predicted results are not reliable enough, GS algorithm is adopted to solve optimization and further a hybrid machine learning model GS-LightGBM is proposed.The tight sandstone formation of member of Chang 4+5 in western Jiyuan Oilfield is validation targets, and two experiments are designed to reveal prediction capability of the proposed model.In order to highlight validation effect, SVM and XGBoost are introduced as comparative predictors.Experimental results manifest GS-XGBoost and GS-LightGBM have the similar and also the highest marks in the prediction performance of accuracy, F1-score, and AUC, while computing time of GS-LightGBM is only 1/23 shorter than that of GS-XGBoost.The results demonstrate the proposed model is capable to rapidly figure out the predicted lithologies based on guarantee of high prediction accuracy, proving its better applicable prospect and generalization in the study field of lithology prediction of tight sandstone formation.
- tight sandstone formation,
- lithology prediction,
- SVM model,
- XGBoost model,
- LightGBM model,
- GS optimizing algorithm

FullText(HTML)

References(23)

References

[1]	周林, 刘皓天, 周坤, 等. 致密砂岩储层"甜点"识别及评价方法[J]. 地质科技通报, 2020, 39(4): 165-173. https://dzkjqb.cug.edu.cn/CN/abstract/abstract10012.shtml Zhou L, Liu H T, Zhou K, et al. "Sweet spot" identification and evaluation of tight sandstone reservoir[J]. Bulletin of Geological Science and Technology, 2020, 39(4): 165-173(in Chinese with English abstract). https://dzkjqb.cug.edu.cn/CN/abstract/abstract10012.shtml
[2]	李峰峰, 郭睿, 余义常. 层序地层划分方法进展及展望[J]. 地质科技情报, 2019, 38(4): 215-224. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201904022.htm Li F F, Guo R, Yu Y C. Progress and prospect of the division of sequence stratigraphy[J]. Geological Science and Technology Information, 2019, 38(4): 215-224(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201904022.htm
[3]	刘惠民, 郑金凯, 赵文山, 等. 深层致密砂岩储层脆性指数评价新方法[J]. 地质力学学报2019, 25(4): 492-500. https://www.cnki.com.cn/Article/CJFDTOTAL-DZLX201904005.htm Liu H M, Zheng J K, Zhao W S, et al. A new method for evaluation brittleness index of deep tight sandstone reservoir[J]. Journal of Geomechanics, 2019, 25(4): 492-500(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZLX201904005.htm
[4]	韦阿娟. 渤海海域中生界火成岩岩性测井识别技术及应用[J]. 地质科技情报, 2015, 34(6): 207-213. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201506030.htm Wei A J. Well-logging identification technique and its application in Mesozoic igneous rocks in Bohai Sea area[J]. Geological Science and Technology Information, 2015, 34(6): 207-213(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ201506030.htm
[5]	赵建, 高福红. 测井资料交会图法在火山岩岩性识别中的应用[J]. 世界地质, 2003, 22(2): 136-140. doi: 10.3969/j.issn.1004-5589.2003.02.006 Zhao J, Gao F H. Application of crossplots based on well log data in identifying volcanic lithology[J]. Global Geology, 2003, 22(2): 136-140(in Chinese with English abstract). doi: 10.3969/j.issn.1004-5589.2003.02.006
[6]	吴磊, 徐怀民, 季汉成. 基于交会图和多元统计法的神经网络技术在火山岩识别中的应用[J]. 石油地球物理勘探, 2006, 41(1): 81-86. doi: 10.3321/j.issn:1000-7210.2006.01.016 Wu L, Xu H M, Ji H C. Application of neural network technique based on crossplot and multielement statistics to recognition of volcanic rocks[J]. Oil Geophysical Prospecting, 2006, 41(1): 81-86(in Chinese with English abstract). doi: 10.3321/j.issn:1000-7210.2006.01.016
[7]	范训礼, 戴航, 张新家, 等. 神经网络在岩性识别中的应用[J]. 测井技术, 1999, 23(1): 50-52. doi: 10.3969/j.issn.1004-1338.1999.01.012 Fan X L, Dai H, Zhang X J, et al. Application of neural network in lithology identification[J]. Well Logging Technology, 1999, 23(1): 50-52(in Chinese with English abstract). doi: 10.3969/j.issn.1004-1338.1999.01.012
[8]	李政宏, 刘永福, 张立强, 等. 数据挖掘方法在测井岩性识别中的应用[J]. 断块油气藏, 2019, 26(6): 713-718. https://www.cnki.com.cn/Article/CJFDTOTAL-DKYT201906008.htm Li Z H, Liu Y F, Zhang L Q, et al. Application of data mining method in lithology identification using well log[J]. Fault-Block Oil & Gas Field, 2019, 26(6): 713-718(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DKYT201906008.htm
[9]	Chen T, Guestrin C. XGBoost: A scalable tree boosting system[C]//Anon. Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining. New York, USA: ACM, 2016.
[10]	卢新卫, 金章东. 前馈神经网络的岩性识别方法[J]. 石油与天然气地质, 1999, 20(1): 82-84. doi: 10.3321/j.issn:0253-9985.1999.01.019 Lu X W, Jin Z D. Method of lithologic recognizing based on feedforward neural network[J]. Oil and Gas Geology, 1999, 20(1): 82-84(in Chinese with English abstract). doi: 10.3321/j.issn:0253-9985.1999.01.019
[11]	张洪, 邹乐君, 沈晓华. BP神经网络在测井岩性识别中的应用[J]. 地质与勘探, 2002, 38(6): 63-65. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKT200206015.htm Zhang H, Zou L J, Shen X H. The application of BP neural network in well lithology identification[J]. Geology and Prospecting, 2002, 38(6): 63-65(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-DZKT200206015.htm
[12]	林香亮, 朱建伟, 刘光涛, 等. 基于PCA-SVM的砂砾岩岩性识别[J]. 长江大学学报: 自然科学版, 2020, 17(1): 21-26. doi: 10.3969/j.issn.1673-1409.2020.01.005 Lin X L, Zhu J W, Liu G T, et al. Lithologic identification of glutenite based on PCA-SVM[J]. Journal of Yangtze University: Natural Science Edition, 2020, 7(1): 21-26(in Chinese with English abstract). doi: 10.3969/j.issn.1673-1409.2020.01.005
[13]	石锁, 余继峰, 曹慧涛, 等. 基于高斯核SVM的地层岩性识别: 以东濮凹陷上古生界碎屑岩为例[J]. 中国科技论文, 2020, 15(1): 112-118. doi: 10.3969/j.issn.2095-2783.2020.01.017 Shi S, Yu J F, Cao H T, et al. Reservoir lithology identification based on SVM using radial basis function: An example of Upper Paleozoic clastic rock in Dongpu Sag[J]. China Science Paper, 2020, 15(1): 112-118(in Chinese with English abstract). doi: 10.3969/j.issn.2095-2783.2020.01.017
[14]	Dev V A, Eden M R. Formation lithology classification using scalable gradient boosted decision trees[J]. Computers & Chemical Engineering, 2019, 128: 392-404. http://www.sciencedirect.com/science/article/pii/S0098135419302200
[15]	Sun Z, Jiang B, Li X, et al. A data-driven approach for lithology identification based on parameter-optimized ensemble learning[J]. Energies, 2020, 13(15): 3903. doi: 10.3390/en13153903
[16]	Ke G L, Meng Q, Finley T, et al. Light GBM: A highly efficient gradient boosting decision tree[C]//Anon. Proceedings of the 31st international conference on neural information processing systems. California, USA: ACM, 2017.
[17]	Zhang X X, Deng T, Jia G Z. Nuclear spin-spin coupling constants prediction based on XGboost and lightGBM algorithms[J]. Molecular Physics, 2019, 118(14): 1-10. doi: 10.1080/00268976.2019.1696478
[18]	韩学辉, 卢时林, 支乐菲, 等. 应用最小二乘支持向量机识别J13井区杜家台油层岩性[J]. 特种油气藏, 2011, 18(6): 18-21. doi: 10.3969/j.issn.1006-6535.2011.06.005 Han X H, Lu S L, Zhi L F, et al. Identification of the lithology of Dujiatai Formation in Well J13 block with east squares support vector machine[J]. Special Oil and Gas Reservoirs, 2011, 18(6): 18-21(in Chinese with English abstract). doi: 10.3969/j.issn.1006-6535.2011.06.005
[19]	邓呈祥, 高文利, 潘和平, 等. 庐枞矿集区科学钻探的岩性识别方法[J]. 物探与化探, 2015, 39(6): 1144-1149. https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201506008.htm Deng C X, Gao W L, Pan H P, et al. Lithologic identification method in scientific drilling of the Luzong ore district[J]. Geophysical & Geochemical Exploration, 2015, 39(6): 1144-1149(in Chinese with English abstract). https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201506008.htm
[20]	Tukey J W. Mathematics and the picturing of data[C]//Anon. Proceedings of the international congress of mathematicians. Vancouver, USA: BC, 1975.
[21]	Han S, Horsfield B, Zhang J, et al. Hydrocarbon generation kinetics of lacustrine Yanchang shale in southeast Ordos Basin, North China[J]. Energy & Fuels, 2014, 28(9): 5632-5639. doi: 10.1021/ef501011b
[22]	Liu H, Li X, Liao J, et al. Genesis of the high gamma sandstone of the Yanchang Formation in the Ordos Basin[J]. China Petroleum Science, 2013, 10(1): 50-54. doi: 10.1007/s12182-013-0248-7
[23]	Li J, Zhou S, Li Y, et al. Effect of organic matter on pore structure of mature lacustrine organic-rich shale: A case study of the Triassic Yanchang shale, Ordos Basin, China[J]. Fuel, 2016, 185: 421-431. doi: 10.1016/j.fuel.2016.07.100

Relative Articles

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article Metrics

Article Views(755) PDF Downloads(567)

Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model

doi: 10.19509/j.cnki.dzkq.2021.0416

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model

doi: 10.19509/j.cnki.dzkq.2021.0416

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Export File

Citation

Format

Content