GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples

Awaiting release License 

This dataset contains example files and Jupyter Notebooks associated with the Geothermal Operational Optimization using Machine Learning (GOOML) framework, specifically for the fictional Kahunanui (KHN) geothermal power plant. The dataset includes synthetic time series data, configuration files, trained machine learning models, and a collection of example notebooks demonstrating data curation, historical modeling, regression, neural networks, hindcast modeling, forecasting, pressure solvers, and genetic optimization. These materials showcase GOOML's capabilities in modeling and optimizing geothermal power plant operations.

The submission includes supporting resources such as system diagrams, well equations, and flash plant dimensions used in constructing the fictional Kahunanui steam field. A data dictionary is provided within the time series data archive, detailing data labels, descriptions, and units. Additionally, webinar slides and a recording of a GOOML overview presentation are included. While example notebooks are provided as PDFs, they cannot be executed without access to the proprietary GOOML codebase, which is not publicly available. Users should note that additional unreleased files are required to run the models and reproduce results. Additionally, an associated dataset for the GOOML Big Kahuna fictional power plant is linked, containing forecast modeling and genetic optimization files.

Citation Formats

TY - DATA AB - This dataset contains example files and Jupyter Notebooks associated with the Geothermal Operational Optimization using Machine Learning (GOOML) framework, specifically for the fictional Kahunanui (KHN) geothermal power plant. The dataset includes synthetic time series data, configuration files, trained machine learning models, and a collection of example notebooks demonstrating data curation, historical modeling, regression, neural networks, hindcast modeling, forecasting, pressure solvers, and genetic optimization. These materials showcase GOOML's capabilities in modeling and optimizing geothermal power plant operations. The submission includes supporting resources such as system diagrams, well equations, and flash plant dimensions used in constructing the fictional Kahunanui steam field. A data dictionary is provided within the time series data archive, detailing data labels, descriptions, and units. Additionally, webinar slides and a recording of a GOOML overview presentation are included. While example notebooks are provided as PDFs, they cannot be executed without access to the proprietary GOOML codebase, which is not publicly available. Users should note that additional unreleased files are required to run the models and reproduce results. Additionally, an associated dataset for the GOOML Big Kahuna fictional power plant is linked, containing forecast modeling and genetic optimization files. AU - Taverna, Nicole A2 - Buster, Grant A3 - Konstantopoulos, Iraklis A4 - Weers, Jon A5 - Siratovich, Paul A6 - Blair, Andy DB - Geothermal Data Repository DP - Open EI | National Renewable Energy Laboratory DO - KW - geothermal KW - energy KW - machine learning KW - GOOML KW - power plant KW - optimization KW - genetic optimization KW - regression KW - neural network KW - operations KW - synthetic data KW - Kahunanui KW - forecast KW - hindcast KW - data curation KW - inputs KW - outputs KW - configuration KW - example KW - phygnn KW - physics guided neural networks KW - steamfield KW - steam field KW - wells KW - flash plants KW - processed data KW - python KW - jupyter notebook KW - model KW - modeling KW - code LA - English DA - 2023/01/30 PY - 2023 PB - Upflow T1 - GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples UR - https://gdr.openei.org/submissions/1466 ER -
Export Citation to RIS
Taverna, Nicole, et al. GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples. Upflow, 30 January, 2023, Geothermal Data Repository. https://gdr.openei.org/submissions/1466.
Taverna, N., Buster, G., Konstantopoulos, I., Weers, J., Siratovich, P., & Blair, A. (2023). GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples. [Data set]. Geothermal Data Repository. Upflow. https://gdr.openei.org/submissions/1466
Taverna, Nicole, Grant Buster, Iraklis Konstantopoulos, Jon Weers, Paul Siratovich, and Andy Blair. GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples. Upflow, January, 30, 2023. Distributed by Geothermal Data Repository. https://gdr.openei.org/submissions/1466
@misc{GDR_Dataset_1466, title = {GOOML Kahunanui Data Curation, Historical Modeling, Forecast Modeling, and Genetic Optimization Examples}, author = {Taverna, Nicole and Buster, Grant and Konstantopoulos, Iraklis and Weers, Jon and Siratovich, Paul and Blair, Andy}, abstractNote = {This dataset contains example files and Jupyter Notebooks associated with the Geothermal Operational Optimization using Machine Learning (GOOML) framework, specifically for the fictional Kahunanui (KHN) geothermal power plant. The dataset includes synthetic time series data, configuration files, trained machine learning models, and a collection of example notebooks demonstrating data curation, historical modeling, regression, neural networks, hindcast modeling, forecasting, pressure solvers, and genetic optimization. These materials showcase GOOML's capabilities in modeling and optimizing geothermal power plant operations.

The submission includes supporting resources such as system diagrams, well equations, and flash plant dimensions used in constructing the fictional Kahunanui steam field. A data dictionary is provided within the time series data archive, detailing data labels, descriptions, and units. Additionally, webinar slides and a recording of a GOOML overview presentation are included. While example notebooks are provided as PDFs, they cannot be executed without access to the proprietary GOOML codebase, which is not publicly available. Users should note that additional unreleased files are required to run the models and reproduce results. Additionally, an associated dataset for the GOOML Big Kahuna fictional power plant is linked, containing forecast modeling and genetic optimization files.}, url = {https://gdr.openei.org/submissions/1466}, year = {2023}, howpublished = {Geothermal Data Repository, Upflow, https://gdr.openei.org/submissions/1466}, note = {Accessed: 2025-05-06} }

Details

Data from Jan 30, 2023

Last updated Mar 31, 2025

Submitted Mar 13, 2025

Organization

Upflow

Contact

Paul Siratovich

Authors

Nicole Taverna

National Renewable Energy Laboratory

Grant Buster

National Renewable Energy Laboratory

Iraklis Konstantopoulos

Upflow

Jon Weers

National Renewable Energy Laboratory

Paul Siratovich

Upflow

Andy Blair

Upflow

DOE Project Details

Project Name Geothermal Operational Optimization with Machine Learning (GOOML)

Project Lead Angel Nieto

Project Number EE0008766

Share

Submission Downloads