DocumentCode :
480629
Title :
Application Genetic Neural Network in Lithology Recognition and Prediction: Evidence from China
Author :
Shao, Yuxiang ; Chen, Qing
Author_Institution :
Sch. of Comput. Sci. & Technol., China Univ. of Geosci., Wuhan
Volume :
2
fYear :
2008
fDate :
20-22 Dec. 2008
Firstpage :
536
Lastpage :
539
Abstract :
The BP neural network algorithm has characteristics of slow convergence speed and local minimum value which could cause the loss of global optimal solution. In order to eliminate the shortcoming of BP neutral network algorithm, genetic algorithm is been put forward to optimize authority value and threshold value of BP nerve network. This paper establishes genetic neural network model. Study has been conducted on lithology recognition prediction using genetic neutral network model. The result shows that this model has significant advantages inspect of fast convergence speed, good generalization ability and not easy to yield minimal local results. In generally, this model exhibits good representation and strong prediction ability, and is suitable for recognition of lithology, lithofacies and sedimentary facies as well as geological research like deposit prediction and rock and mineral recognition.
Keywords :
backpropagation; genetic algorithms; geophysics computing; neural nets; rocks; sediments; China; backpropagation; genetic algorithm; genetic neural network; lithofacies; lithology prediction; lithology recognition; mineral recognition; rock recognition; sedimentary facies; Application software; Character recognition; Computer science; Convergence; Genetic algorithms; Geology; Mathematical model; Minerals; Neural networks; Predictive models; BP neural network; genetic algorithm; lithology recognition; optimization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Information Technology Application, 2008. IITA '08. Second International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-0-7695-3497-8
Type :
conf
DOI :
10.1109/IITA.2008.432
Filename :
4739822
Link To Document :
بازگشت