Reservoir characterization plays a crucial role in integrated exploration. At the same time, the two main challenges continually puzzle the reservoir characterization, one is that the limitation of wells’ lateral resolution constrains the reservoir characterization at locations where are far from the wells. Another is that evaluating the quality of reservoir via a single reservoir parameter is usually insufficient. A modified reservoir characterization method is proposed in this abstract. Firstly, we apply a random forest algorithm to predict reservoir parameters from elastic parameters. Secondly, fuzzy logic algorithm is adopted to integrate reservoir parameters to craft reservoir description. Numerical experiment on the field data confirms the validity of the proposed method.
Presentation Date: Tuesday, October 13, 2020
Session Start Time: 9:20 AM
Presentation Time: 9:45 AM
Location: Poster Station 9
Presentation Type: Poster
