Optimization of Production and Injection of Geothermal Fields: A Machine Learning Approach
- Key words
- optimization, proxy, tough2, machine learning, Kizildere
- Conference
- World Geothermal Congress
- Year
- 2020
- Session
- Field Management
- Language
- English
- Paper number
- 24034
Full text
1011 KB, opens in a new tab
Abstract
Optimizing field injection and production requires a numerical model, typically consist of thousands of grid blocks. Optimization carried out using such a model usually takes a very long time. If the numerical model is replaced by accurate proxy model, run-time can be significantly reduced. A numerical model has been developed using Tough2 to optimize the production of Kizildere geothermal field. A proxy model developed in python is used to optimize the production and injection rates of the field. Proxy model results are consistent with Tough2 numeric model. This approach significantly reduces time and effort.
Copyright 2020, International Geothermal Association. Readers who download papers from this site should honour the copyright of the original authors, and may not copy or distribute the work further without the permission of the original publisher.