Characterization of petroleum reservoir based on self organizing maps
基于自组织映射网络的油藏表征模型*

SOM neural networks can implement feature preserving, dimension reduction and data visualization. This paper proposed the SOM neural network for the petroleum parameter characterization. Simulation on the well-log data of Zhenyuan- Jingchuan area, in Gansu, shows that this algorithm is practicable and effective for actual reservoir modeling.