物探与化探2024，Vol.48Issue(2)：428-436,9.DOI:10.11720/wtyht.2024.1260
基于特征加权的KNN模型岩性识别方法
A method for identifying lithology based on a feature-weighted KNN model
摘要
Abstract
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.How-ever,the physical property data of different rocks frequently overlap to some extent,posing challenges to accurate lithology identifica-tion using cross plots alone.The K-nearest neighbor(KNN)model is suitable for multi-class classification since it is a simple and di-rect machine learning method with high accuracy and sensitivity.This study introduced a feature-weighted KNN model for lithology i-dentification.In this model,different weights were assigned to different features by combining the conventional KNN model with the in-formation gain of attribute features.This allowed for intuitive reflection of the importance of attribute features to classification.Experi-ments 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.关键词
KNN/岩性识别/信息增益/特征权重Key words
KNN/lithology identification/information gain/feature weight分类
天文与地球科学引用本文复制引用
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):428-436,9.基金项目
中海石油有限公司科技项目"中国近海盆地潜在富油凹陷资源潜力、成藏机制与突破方向"之课题"中国近海潜在富油凹陷深部构造差异性研究"项目(CCL2021RCPS0167KQN) （CCL2021RCPS0167KQN）
