AUTHOR=Zhan Weiyun , Li Haitao , Wu Xuefeng , Zhang Jingyue , Liu Chenxi , Zhang Dongming 

TITLE=Research on neural network prediction method for upgrading scale of natural gas reserves

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1253495

DOI=10.3389/feart.2023.1253495

ISSN=2296-6463

ABSTRACT=With the gradual decline in natural gas production, the upgrading of reserves has become one of the important issues in natural gas exploration and development. However, traditional methods for reserve upgrading prediction are often based on experience and rules, which suffer from subjectivity and unreliability. Therefore, A prediction method is proposed based on neural networks to improve the accuracy and reliability of reserve upgrading prediction in this paper. To achieve this goal, by collecting the relevant data of natural gas exploration and development in Sichuan Basin, including geological parameters, production parameters and other indicators, and processing and analyzing the data, the relevant characteristics of reserves improvement are extracted. Subsequently, a neural network model based on a multilayer perceptron (MLP) was constructed, and the backpropagation algorithm was used for training and optimization. The research results show that the neural network model constructed in this study can effectively predict reserve upgrading with high accuracy and reliability. Experiments demonstrate that the prediction accuracy of the model can exceed 90%, significantly outperforming traditional prediction methods. The proposed method in this study exhibits good stability and reliability, making it suitable for a wider range of natural gas domains.