基于MobileNetV2的岩石薄片岩性识别  

Rock Thin Slice Lithology Identification Based on MobileNetV2

作　　者：王婷婷[1,2] 黄志贤 王洪涛 杨明昊 赵万春 Wang Tingting;Huang Zhixian;Wang Hongtao;Yang Minghao;Zhao Wanchun(School of Electrical Information Engineering,Northeast Petroleum University,Daqing 163318,Heilongjiang,China;Key Laboratory of Network and Intelligent Control in Heilongjiang Province,Northeast Petroleum University,Daqing 163318,Heilongjiang,China;Institute of Unconventional Oil&Gas,Northeast Petroleum University,Daqing 163318,Heilongjiang,China)

机构地区：[1]东北石油大学电气信息工程学院,黑龙江大庆163318 [2]东北石油大学黑龙江省网络与智能控制重点实验室,黑龙江大庆163318 [3]东北石油大学非常规油气研究院,黑龙江大庆163318

出　　处：《吉林大学学报（地球科学版）》2024年第4期1432-1442,共11页Journal of Jilin University：Earth Science Edition

基　　金：国家自然科学基金项目(52074088,52174022,51574088,51404073);黑龙江省教育科学规划课题(GJB1422142);东北石油大学特色领域团队专项项目(2022TSTD-03);黑龙江省博士后科研启动项目(LBH-Q20074,LBH-Q21086);黑龙江省高校基本科研业务费项目(2022TSTD-04)。

摘　　要：岩石薄片的岩性识别是地质分析中不可或缺的一环,其精准度直接影响后续地层岩石种类、性质和矿物成分等信息的确定,对于地质勘探和矿产开采具有重要意义。为了快速准确地识别岩性,本文提出了一种改进的MobileNetV2轻量化模型,通过选取5种岩石类型共3 700张岩石薄片图像进行岩性识别。在MobileNetV2的倒残差结构中嵌入坐标注意力机制,融合图像中多种矿物的全局特征信息。此外,改进MobileNetV2中的分类器,降低模型的参数量和计算复杂度,从而提高模型的运算速度和效率,并采用带泄露线性整流函数(leaky rectified linear unit, Leaky ReLU)作为激活函数,避免网络训练中的梯度消失问题。实验结果表明,本文提出的改进后的MobileNetV2模型大小仅为2.30 MB,在测试集上的精确率、召回率、F_(1)值分别为91.24%、90.18%、90.70%,具有较高的准确性,相比于SqueezeNet、ShuffleNetV2等同类型的轻量化网络,分类效果最好。The lithology identification of rock thin sections is an indispensable part of geological analysis,and its precision directly affects the determination of the types,properties,mineral composition,and other microscopic information of subsequent stratigraphic rock,which is of great significance for geological exploration and mineral mining.In order to identify lithology quickly and accurately,an improved MobileNetV2 lightweight model is proposed to address the complex and diverse mineral composition in rock slices,which identifies lithology from a total of 3700 rock slice images of five types of rocks.The coordinate attention mechanism is embedded in the inverse residual structure of MobileNetV2 to fuse global feature information of multiple minerals in the image.In addition,the classifier in MobileNetV2 is improved to reduce the number of parameters and computational complexity of the model,so as to improve the computing speed and efficiency of the model,and the leaky rectified linear unit(Leaky ReLU)is used as the activation function to avoid the problem of gradient vanishing in network training.Experimental results show that the improved MobileNetV2 model proposed in this paper has a size of only 2.30 MB,and the precision,recall rate,and F_(1) value on the test set are 91.24%,90.18%,and 90.70%,respectively,which has high accuracy,and has the best classification effect compared with similar lightweight networks such as SqueezeNet and ShuffleNetV2.

关 键 词：岩石薄片图像 轻量化神经网络 MobileNetV2 坐标注意力机制 岩性识别 

分 类 号：P585.1[天文地球—岩石学] TP183[天文地球—地质学]