大地电磁人工神经网络反演

来源期刊:中南大学学报(自然科学版)2015年第5期

论文作者:王鹤 蒋欢 王亮 席振铢 张道军

文章页码:1707 - 1715

关键词:大地电磁;神经网络;反演

Key words:magnetotelluric; neural network; inversion

摘    要:为提高大地电磁非线性反演的计算效率和精度,将人工神经网络引入大地电磁数据反演。神经网络输入为已知地电模型的视电阻率数组,输出为地电模型参数。采用BP算法(back propagation algorithm)进行学习训练,通过信息正向传播和误差反向传播,迭代计算得出神经网络连接权值的最优值;再将训练好的神经网络对未知模型的视电阻率进行反演。对2层和3层大地电磁模型分别建立神经网络并测试反演,研究结果表明:该反演方法能实时准确地逼近真实模型,验证了该方法的可行性和有效性。

Abstract: The artificial neural network(ANN) was studied to improve the magnetotelluric inversion operation efficiency and calculation accuracy. The input of neural network was apparent resistivity of the known models, and the output of neural network was the geoelectric parameters. The neural network was trained by back propagation algorithm, which contains the methods of information forward propagation and error back propagation. The best weight of network calculated by the training work was used to test the unknown model patterns, which is the inversion process. The networks for two-layer model and three-layer model were set up respectively. The results show that the neural network inversion is feasible and effective.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号