人工神经网络及其在地学中的应用综述  

Review on artificial neural networks and their applications in geoscience

作　　者：王良玉[1] 张明林 祝洪涛[1] 刘洋[1] WANG Liangyu;ZHANG Minglin;ZHU Hongtao;LIU Yang(Geologic Party No.243,CNNC,Chifeng Inner Mongolia 024000,China;China Geological Bureau of Nuclear Industry,Beijing 100013,China)

机构地区：[1]核工业二四三大队,内蒙古赤峰024000 [2]中国核工业地质局,北京100013

出　　处：《世界核地质科学》2021年第1期15-26,共12页World Nuclear Geoscience

基　　金：中国核工业地质局基础项目《铀矿勘查数据综合应用系统建设》(编号:201812)资助。

摘　　要：人工神经网络(ANN)是一种模仿人脑神经网络结构和功能的信息处理系统,是一种分布式并行处理信息的抽象数学模型,现已在许多科学领域得以成功应用。在地球科学领域,人工神经网络最早应用于地球物理反演问题,随后逐渐扩展至其他领域。通过简要介绍人工神经网络的发展历程、基本特征及其模型,对地学领域中常用的人工神经网络模型进行了简单对比,并论述了其在地学领域中的应用特点,总结了近年来人工神经网络在地学领域中的主要应用,着重从判别分类、模式识别、预测评价以及信息数据处理等方面的应用进行了详细阐述。同时,结合地学领域的实际特点和人工智能领域中大量出现的优化理论和技术,分析认为人工神经网络在地学领域中的应用将逐渐呈现多种技术和深度学习的相融合态势,且在地学领域中应用效果会日益显著。这些探讨和分析对推动地学工作数字化、智能化具有参考意义。Artificial neural network (ANN) is an information processing system that imitates the structure and function of human brain neural networks,which is an abstract mathematical model for distributed and parallel information processing. It has been successfully applied in many scientific fields. In the field of geoscience,artificial neural network was first applied to geophysical inversion problems,and then gradually expanded to other fields. This paper briefly introduced the development process, basic characteristics and models of artificial neural network,and made a simple comparison of artificial neural network models commonly used in the field of geosciences. In addition,this paper also discussed the application characteristics of artificial neural networks in the field of geoscience,and summarized the main applications of artificial neural networks in the field of geoscience in recent years,focusing on the application of discriminant classification,pattern recognition,evaluation and prediction,and information data processing. Combined with the actual characteristics of geoscience and the emergence of a large number of optimization theories and technologies in the field of artificial intelligence,this paper also analyzed that the application of artificial neural networks in the field of geoscience will gradually present a trend of integration of various technologies and deep learning,and the application effect in the field of geoscience will be increasingly significant.

关 键 词：人工神经网络(ANN) 地球科学 深度学习 智能化 

分 类 号：P5[天文地球—地质学] TP389.1[自动化与计算机技术—计算机系统结构]