A method for identifying lithology based on a feature-weighted KNN model
GUO Yu-Shan1(), WANG Wan-Yin1,2,3()
1. School of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China 2. Key Laboratory of Marine Geology & Environment, Qingdao 266071, China 3. National Engineering Research Center of Offshore Oil and Gas Exploration, Beijing 100028, China
Lithology identification, as a major geological task, strongly underpins the exploration of solid minerals, oil, and gas. Since the physical properties of rocks bridge lithologies and geophysical fields, their differences can be used for lithology identification. However, the physical property data of different rocks frequently overlap to some extent, posing challenges to accurate lithology identification using cross plots alone. The K-nearest neighbor (KNN) model is suitable for multi-class classification since it is a simple and direct machine learning method with high accuracy and sensitivity. This study introduced a feature-weighted KNN model for lithology identification. In this model, different weights were assigned to different features by combining the conventional KNN model with the information gain of attribute features. This allowed for intuitive reflection of the importance of attribute features to classification. Experiments show that compared to the conventional KNN model, the feature-weighted KNN model can more significantly identify lithologic boundaries, thus improving the overall accuracy and stability of lithology identification.
郭雨姗, 王万银. 基于特征加权的KNN模型岩性识别方法[J]. 物探与化探, 2024, 48(2): 428-436.
GUO Yu-Shan, WANG Wan-Yin. A method for identifying lithology based on a feature-weighted KNN model. Geophysical and Geochemical Exploration, 2024, 48(2): 428-436.
Feng G H, Wu J X. A literature review on the improvement of KNN algorithm[J]. Library and Information Service, 2012, 56(21):97-100,118.
[25]
Stone M. Cross-validatory choice and assessment of statistical predictions[J]. Journal of the Royal Statistical Society Series B:Statistical Methodology, 1974, 36(2):111-133.
Sun A, Zhao L F. K-nearest neighbor algorithm based on information gain and gini impurity[J]. Computer Technology and Development, 2019, 29(9):51-54,116.
[27]
袁彪. 基于机器学习的岩性识别模型研究[D]. 北京: 中国地质大学(北京), 2021
[27]
Yuan B. Research on lithology identification Model based on Machine Learning[D]. Beijing: China University of Geosciences (Beijing), 2021.
[28]
范永东. 模型选择中的交叉验证方法综述[D]. 太原: 山西大学, 2013.
[28]
Fan Y D. Review of cross-validation methods in model selection[D]. Taiyuan: Shanxi University, 2013.
Jin J, Liu L J, Shao Y, et al. Discussion on identifying method for Identification of lithologic traps in Junggar Basin by comprehensive geophysical method[J]. Oil Geophysical Prospecting, 2002, 37(3):287-290,299-306.
Yan J Y, Lyu Q T, Chen X B, et al. 3D lithologic mapping test based on 3D inversion of gravity and magnetic data:A case study in Lu-Zong ore concentration district,Anhui Province[J]. Acta Petrologica Sinica, 2014, 30(4):1041-1053.
Fu G M. Lithology identification and stereo mapping based on gravity and magnetic 3D inversion-taking Tongling ore concentration area as an example[D]. Fuzhou: East China Institute of Technology, 2017.
Wu L, Xu H M, Ji H C. Application of neural networks technique based on crosspiot and multielement statistics to recognition of volcanic rocks[J]. Oil Geophysical Prospecting, 2006, 41(1):81-86,122,128.
Zhang T, Mo X W. Complex lithology identification based on crossplot and fuzzy clustering algorithm[J]. Journal of Jilin University:Earth Science Edition, 2007, 37(S1):109-113.
Guan T. Method of lithologic identification based on crossplot and Bayesian cluster analysis algorithm[J]. Science Technology and Engineering, 2013, 13(4):976-979.
Zhang Y Q. Discussion on the application of logging data crossplot method in volcanic rock lithology identification[J]. West-China Exploration Engineering, 2019, 31(4):53-54.
Xu Z H, Ma W, Li S C, et al. Lithology identification:Method,research status and intelligent development trend[J]. Geological Review, 2022, 68(6):2290-2304.
[11]
Wang X D, Yang S C, Zhao Y F, et al. Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field,Jiyang depression[J]. Journal of Petroleum Science and Engineering, 2018, 166:157-174.
doi: 10.1016/j.petrol.2018.03.034
[12]
Silva A A, Tavares M W, Carrasquilla A, et al. Petrofacies classification using machine learning algorithms[J]. Geophysics, 2020, 85(4):WA101-WA113.
Cai Z Y, Lu B L, Xiong S Q, et al. Lithology identification based on Bayesian probability using adaptive kernel density[J]. Geophysical and Geochemical Exploration, 2020, 44(4):919-927.
Mou D, Zhang L C, Xu C L. Comparison of three classical machine learning algorithms for lithology identification of volcanic rocks using well logging data[J]. Journal of Jilin University:Earth Science Edition, 2021, 51(3):951-956.
Chen Y L, Li G L, Yang Z X, et al. Identification of lithology and lithofacies of Chang 7 reservoir in Heshui area by KNN algorithm[J]. Well Logging Technology, 2020, 44(2):182-185.
Liu S C, Zhang Z L. A multi-stage classification KNN algorithm based on center vector[J]. Computer Engineering & Science, 2017, 39(9):1758-1764.
[17]
Chen Y W, Zhou L D, Tang Y, et al. Fast neighbor search by using revised k-d tree[J]. Information Sciences, 2019, 472:145-162.
doi: 10.1016/j.ins.2018.09.012
Xiao H H, Duan Y M. Research on improvement of KNN algorithm based on correlation distance of attribute values[J]. Computer Science, 2013, 40(S2):157-159,187.
Zhao T T, Zhang C L, Zhang C Y, et al. Application of KNN classification model based on fuzzy entropy in lithology recognition[J]. Computer Engineering and Applications, 2018, 54(24):260-265.
doi: 10.3778/j.issn.1002-8331.1709-0084
Zhu H, Cao N, Lu H, et al. Non-intrusive load identification method based on feature weighted KNN[J]. Electronic Measurement Technology, 2022, 45(8):70-75.
[23]
Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1):21-27.
doi: 10.1109/TIT.1967.1053964
