基于多尺度卷积神经网络的多源数据融合岩性分类方法  

Multiscale Convolutional Neural Network-Based Lithology Classification Method for Multisource Data Fusion

作　　者：戴嵩 孙喜明 张精明 朱永山[2] 王斌[1] 宋冬梅[1] Dai Song;Sun Ximing;Zhang Jingming;Zhu Yongshan;Wang Bin;Song Dongmei(College of Ocean and Space Information,China University of Petroleum(East China),Qingdao 266580,Shandong,China;Bureau of Geophysical Prospecting INC.,China National Petroleum Corporation,Zhuozhou 072750,Hebei,China)

机构地区：[1]中国石油大学(华东)海洋与空间信息学院,山东青岛266580 [2]中国石油集团东方地球物理勘探有限责任公司,河北涿州072750

出　　处：《激光与光电子学进展》2024年第14期363-372,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41701513、41772350、61371189);山东省自然科学基金(ZR2022MD015);其他项目(HX20220856)。

摘　　要：在岩性分类任务中,利用单一数据源获取的特征信息有限,因此多源数据融合成为提高岩性分类准确性的重要手段。航空遥感影像和数字高程模型作为典型的遥感数据源,可以提供互补的光谱和高程信息。为了提升岩性分类的精度,提出一种融合通道空间注意力机制与多尺度卷积神经网络的多源遥感数据岩性分类方法。该方法通过设计多尺度空洞卷积模块,增强卷积神经网络对航空遥感影像和数字高程模型深层特征的学习能力,从而更好地捕捉特征的空间关系,并有效消除异构数据在原始数据空间上的结构差异。此外,通过设计局部和全局的多尺度通道空间注意力模块,以自适应方式为多源数据的光谱通道和空间区域赋予不同的权重,从而利用特征的显著性实现更有针对性的网络训练,进一步提升模型的分类性能。最后,以四川某盆地为研究区域进行有效性验证。实验结果表明,所提方法在总体分类精度、平均分类精度等评价指标上明显优于4种典型的机器学习方法,证实了所提多源数据融合方法能够充分利用不同数据源的互补优势,从而有效提高地质岩性的判别精度。In the task of lithology classification,the feature information obtained from a single data source is limited.Hence,multisource data fusion is an important means by which to improve the accuracy of lithology classification.As typical remote sensing data sources,aerial remote sensing images and digital elevation models can provide complementary spectral and elevation information.In order to improve the accuracy of lithology classification,a new lithology classification method for multisource remote sensing data is proposed.The proposed method combines the spatial attention mechanisms of channel and multiscale convolutional neural networks.Additionally,this method enhances the learning ability of convolutional neural networks on deep features of aerial remote sensing images and digital elevation models by designing a multiscale void convolutional module to better capture the spatial relationships of features and effectively eliminate the structural differences of heterogeneous data in the original data space.By designing local and global multiscale channel spatial attention modules,different weights can be assigned to spectral channels and spatial regions of multisource data in an adaptive way to both realize more targeted training of the network by using the significance of features and further improve the classification performance of the model.Finally,a basin in Sichuan province is taken as the study area to validate the proposed techniques.The experimental results show that the proposed method is significantly better than four typical machine learning methods in the overall accuracy and average accuracy,which proves that the proposed multisource data fusion method can make full use of the complementary advantages of different data sources and effectively improve the discrimination accuracy of geological lithology.

关 键 词：航空遥感影像 数字高程模型 岩性分类 特征融合 卷积神经网络 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]