当前位置: X-MOL 学术Earth Sci. Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Neural network boosted with differential evolution for lithology identification based on well logs information
Earth Science Informatics ( IF 2.8 ) Pub Date : 2020-10-10 , DOI: 10.1007/s12145-020-00533-x
Camila Martins Saporetti , Leonardo Goliatt , Egberto Pereira

Lithology identification of geological beds in the subsurface is fundamental in reservoir characterization. Recently, automated log analysis has an increasing demand in reservoir research and the oil industry. In this context, Machine Learning (ML) techniques arise as a surrogate model to provide lithology identification in a fast way. However, to achieve suitable performance, ML techniques require the adjustment of some parameters, and that can become a hard task, depending on the difficulty of the problem to be solved. This paper presents an Artificial Neural Network (ANN), assisted by an adaptive Differential Evolution (DE) algorithm to classify petrophysical data in the Southern Provence Basin. The main contribution is searching for a competent ANN configuration, including architecture, activation functions, regularization, and training algorithms. The proposed approach outperformed four classifiers and two results previously published. The computational methodology proposed here is able to assist in the classification of petrophysical data, helping to improve the procedure of reservoir characterization and the idealization of the development of production.



中文翻译:

基于差分测井的神经网络基于测井信息识别岩性

地下地质床的岩性识别是储层表征的基础。近来,自动测井分析在储层研究和石油工业中的需求不断增长。在这种情况下,机器学习(ML)技术作为一种替代模型出现,可以快速提供岩性识别。但是,为了获得合适的性能,机器学习技术需要调整一些参数,这取决于要解决的问题的难度,这可能成为一项艰巨的任务。本文提出了一种人工神经网络(ANN),并辅之以自适应差分进化(DE)算法对南普罗旺斯盆地的岩石物理数据进行分类。主要贡献在于寻找合适的ANN配置,包括架构,激活功能,正则化,和训练算法。所提出的方法优于四个分类器和两个先前发布的结果。此处提出的计算方法能够帮助对岩石物理数据进行分类,从而有助于改善储层特征描述过程和生产开发的理想化。

更新日期:2020-10-11
down
wechat
bug