Lithology identification of logging data based on improved neighborhood rough set and AdaBoost

Springer Science and Business Media LLC - Tập 15 - Trang 1201-1213 - 2022
Xialin Zhang1,2,3,4, Qing Sun1,3, Kunyang He1,3, Zhenjiang Wang1,3,4, Jin Wang1,3
1School of Computer Science, China University of Geoscience, Wuhan, China
2State Key Laboratory of Biogeology and Environmental Geology, Wuhan, China
3Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China
4Engineering Technology Innovation Center of Mineral Resources Explorations in Bedrock Zones, Ministry of Natural Resources, Guiyang, China

Tóm tắt

Traditional lithology identification left the problems of low accuracy, recognition efficiency and generalization ability. Facing the logging data with outliers, unbalance and high complexity, we propose a lithology identification method based on an improved neighborhood rough set and AdaBoost. On the basis of the classical neighborhood rough set, the selection of the neighborhood radius and the running time are optimized. The redundant information in logging data is then effectively eliminated. Thus more sensitive logging curves are selected without changing the physical meaning of logging attributes. Then the selected data are input into the AdaBoost model to construct a lithology identification model. About 54,000 samples from 5 boreholes are tested in the study area. The accuracy of classification on the test set is about 98.42%. Compared with BP neural network and random forest algorithm, the proposed method owns advantages in recognition accuracy and generalization ability. It can provide help for complex lithology recognition in the study area.

Tài liệu tham khảo

An R, Suo M (2016) Application of attribute reduction and weights calculation through neighborhood rough set. Comput Eng Appl 52(07):160–165 Chawla N, Bowyer K, Hall L, Kegelmeyer W (2020) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357 Cheng G, Guo R, Wu W (2010) Petroleum lithology discrimination based on PSO-LSSVM classification model. International conference on Computer Modeling & Simulation 365-368 Chi H (2020) Study on mineralization forecast of Xinjiang Hongyuntan-Chilongfeng iron mine belt based on improved AdaBoost algorithm. Dissertation, China University of Geosciences (Beijing) Deng C, Pan H, Fang S, Konate A, Qin R (2017) Support vector machine as an alternative method for lithology classification of crystalline rocks. J Geophys Eng 14(2):341–349 Gao Y (2011) New soft margin algorithm adjusting the weights of weak classifiers for AdaBoost. Dissertation, Xidian University Gao Y (2019) Study of reduction algorithm and classifier based on neighborhood rough set. Dissertation, Qingdao University Gu Y, Zhang D, Bao Z, Zhang C (2021) Lithology prediction of tight sandstone reservoirs using GBDT. Prog Geophys:1–13 Hu Q, Yu D, Xie Z (2008) Numerical attribute reduction based on neighborhood granulation and rough approximation. Journal of Softw 09:640–649 Huang L (2008) BP neural network algorithm improvement and application research. Dissertation, Chongqing Normal University Huang X (2017) Study on the relationship between drill logging characteristics and uranium mineralization in sandstone-type uranium deposits. Dissertation, East China University of Technology Jiang A, Jin L, IEEE (2009) Studying the Lithology Identification Method from Well logs Based on DE-SVM. CCDC 2009: 21ST Chinese Control And Decision Conference Vols 1–6 Kang Q (2020) Application of random forest algorithm for anomaly identification of sandstone-type uranium deposits based on well logging data. Dissertation, Jilin University Kong Q, Gong H, Ding X, Hou R (2017) Classification Application Based on Mutual Information and Random Forest Method for High Dimensional Data. 2017 9th International Conference on Intelligent Human-Machine System And Cybernetics (IHMSC 2017) Vol 1 Li H (2012) Statistical learning methods. Tsinghua University Press, Beijing Lin Z (2020) Research and application of attribute reduction algorithm based on neighborhood rough set. Dissertation, Qingdao University Liu M, Li H, Jiang Z (2011) Application of genetic-BP neural network model in lithology identification by logging data in Binchang mining area. Coal Geol Expl 45(09):65–69 Ma L (2016) Research on optimization and improvement of random forests algorithm. Dissertation, Jinan University Mathew J, Pang C, Luo M, Leong W (2018) Classification of imbalanced data by oversampling in kernel space of support vector machines. IEEE Trans Neural Netw Learn Syst 29(9):4065–4076. https://doi.org/10.1109/TNNLS.2017.2751612 Puskarczyk E (2019) Artificial neural networks as a tool for pattern recognition and electrofacies analysis in polish palaeozoic shale gas formations. Acta Geophysica 67(6):1991–2003 Raeesi M, Moradzadeh A, Ardejani F, Rahimi M (2012) Classification and identification of hydrocarbon reservoir lithofacies and their heterogeneity using seismic attributes, logs data and artificial neural networks. J Pet Sci Eng 82-83:151–165 Saporetti C, Goliatt L, Pereira E (2021) Neural network boosted with differential evolution for lithology identification based on well logs information. Earth Sci Inf 14(1):133–140 Song Y, Chen K, Wang X (2011) Geophysical well logging. Petroleum Industry Press, Beijing Sun J, Li Q, Chen M, Ren L, Huang G, Li C, Zhang Z (2019) Optimization of models for a rapid identification of lithology while drilling-a win-win strategy based on machine learning. J Pet Sci Eng 176:321–341 Tewari S, Dwivedi U (2019) Ensemble-based big data analytics of lithofacies for automatic development of petroleum reservoirs. Comput Ind Eng 128:937–947 Wang P (2011) Study on feature selection based on neighborhood rough set. Dissertation, Hebei University of Science and Technology Wu Z (2020) Research on feature selection algorithm based on rough set model extension. Dissertation, Anhui University Xie Y, Zhu C, Lu Y, Zhu Z (2019) Towards optimization of boosting models for formation lithology identification. Math Probl Eng 2019:1–13 Xu Z, Li J, Chen T (2018) Naive bayesian decision tree algorithm combining SMOTE and filter-wrapper and its application. Comput Sci 45(09):65–69 Zhao J, GAO F (2003) Application of crossplots based on well log data in identifying volcanic lithology. Global Geology 2:136–140 Zhou S, Xu Z, Tang X (2010) New method for determining the optimal number of clusters in K-means clustering algorithm. J Comput Appl 46(16):27–31