MSc defence by Agata Rostran Largaespada

Agata Rostran Largaespada from Nicaragua, MSc Fellow in Sustainable Energy Engineering at Reykjavík University will present her MSc project on Monday 2nd of September at 14:00 at Reykjavík University in room M119.  

The title of the project is:
Predicting real-time geothermal well flow rate and enthalpy with machine learning

Agata's supervisors are:
María S. Gudjónsdóttir, Associate Professor, Reykjavík University, Iceland
Egill Júlíusson, CTO at Arctic Green Energy

External examiner is Pálmar Sigurðsson, Project Manager, Reykjavik Energy

Abstract
Geothermal energy is a sustainable energy source offering reliable and renewable energy solutions. However, to accurately measure geothermal well output like flow rate and enthalpy, which produce a two-phase fluid, remains challenging due to the complexity and infrequency when using traditional methods. This thesis addresses these issues by continuing the work of developing a real-time method to measure flow rate and enthalpy from geothermal wells without interrupting operations. The focus is on accurately estimating the flow rate and enthalpy of geothermal fluids using advanced rule-based models and machine learning techniques. By using measurement data from Landsvirkjun's geothermal operations conducted in 2019, 2020, 2021, and 2023, this research integrates data-driven approaches for continuous monitoring and early detection of well performance changes. The study employs a specialized differential pressure orifice plate meter setup at Theistareykir and Bjarnarflag Geothermal Power Plants, providing detailed measurements that are critical for the models. The most effective model employed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for noise reduction, Recursive Feature Elimination with Cross-Validation (RFECV) for precise feature selection, and Random Forest Regression (RFR) with five key features, achieving an RMSE of 0.011. This approach can significantly enhance the efficiency and accuracy of geothermal power production measurements, offering insights into real-time monitoring and operational optimization.