GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files

Buster, Grant; Weers, Jon; Siratovich, Paul; Rossol, Michael; Taverna, Nicole; Blair, Andy; Huggins, Jay

doi:10.15121/1812319

Title: GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files

Dataset
Other Related Research

Abstract

This submission includes example files associated with the Geothermal Operational Optimization using Machine Learning (GOOML) Big Kahuna fictional power plant, which uses synthetic data to model a fictional power plant. A forecast was produced using the GOOML data model framework and fictional input data, and a genetic optimization is included which determines optimal flash plant parameters. The inputs and outputs associated with the forecast and genetic optimization are included. The input and output files consist of data, configuration files, and plots. A link to the Physics-Guided Neural Networks (phygnn) GitHub repository is also included, which augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn is used by the GOOML framework to help integrate its machine learning models into the relevant physics and engineering applications. Note that the data included in this submission are intended to provide a demonstration of GOOML's capabilities. Additional files that have not been released to the public are needed for users to run these models and reproduce these results. Units can be found in the readme data resource.

Authors:

Buster, Grant; Weers, Jon; Siratovich, Paul; Rossol, Michael; Taverna, Nicole; Blair, Andy; Huggins, Jay

Upflow

Publication Date:: 2021-06-30

Other Number(s):: 1314

DOE Contract Number:: EE0008766

Research Org.:: DOE Geothermal Data Repository; Upflow

Sponsoring Org.:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Geothermal Technologies Program (EE-4G)

Collaborations:: Upflow

Subject:: 15 GEOTHERMAL ENERGY; Big Kahuna; GOOML; code; configuration; data; energy; example; flash plants; forecast; genetic optimization; geothermal; inputs; machine learning; model; neural network; operations; optimization; outputs; phygnn; physics guided neural networks; power plant; processed data; python; simulation; steam field; steamfield; synthetic data; wells

OSTI Identifier:: 1812319

DOI:: https://doi.org/10.15121/1812319

Citation Formats


                    Buster, Grant, Weers, Jon, Siratovich, Paul, Rossol, Michael, Taverna, Nicole, Blair, Andy, and Huggins, Jay. GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files.  United States: N. p., 2021. 
        Web.  doi:10.15121/1812319.

Copy to clipboard


                    Buster, Grant, Weers, Jon, Siratovich, Paul, Rossol, Michael, Taverna, Nicole, Blair, Andy, & Huggins, Jay. GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files.  United States.  doi:https://doi.org/10.15121/1812319

Copy to clipboard


                    Buster, Grant, Weers, Jon, Siratovich, Paul, Rossol, Michael, Taverna, Nicole, Blair, Andy, and Huggins, Jay. 2021.  
"GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files".  United States.  doi:https://doi.org/10.15121/1812319.  https://www.osti.gov/servlets/purl/1812319. Pub date:Wed Jun 30 04:00:00 UTC 2021

Copy to clipboard


                    
@article{osti_1812319,

  title        = {GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files},

  author       = {Buster, Grant and Weers, Jon and Siratovich, Paul and Rossol, Michael and Taverna, Nicole and Blair, Andy and Huggins, Jay},

  abstractNote = {This submission includes example files associated with the Geothermal Operational Optimization using Machine Learning (GOOML) Big Kahuna fictional power plant, which uses synthetic data to model a fictional power plant. A forecast was produced using the GOOML data model framework and fictional input data, and a genetic optimization is included which determines optimal flash plant parameters. The inputs and outputs associated with the forecast and genetic optimization are included. The input and output files consist of data, configuration files, and plots. A link to the Physics-Guided Neural Networks (phygnn) GitHub repository is also included, which augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn is used by the GOOML framework to help integrate its machine learning models into the relevant physics and engineering applications. Note that the data included in this submission are intended to provide a demonstration of GOOML's capabilities. Additional files that have not been released to the public are needed for users to run these models and reproduce these results. Units can be found in the readme data resource.},

  doi          = {10.15121/1812319},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {2021},

  month        = {6}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.15121/1812319

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

TEAMER: Crossflow Turbine Fairing Geometry Optimization - Report and CFD Modeling Files

Dataset McEntee, Jarlath

The dataset includes computational fluid dynamics (CFD) models and simulation files for crossflow turbines as well as a detailed project report. The report documents the project undertaken by the Ocean Renewable Power Company (ORPC) to design and optimize a modular fairing for the Modular RivGen Marine Hydrokinetic (MHK) turbine, which enhances the efficient deployment and operation of turbine arrays. The project focused on optimizing the hydrodynamic performance of the fairing using CFD, with an emphasis on two key geometric parameters: the fairing's cross-sectional shape and the spacing between the rotor and the fairing. The analysis aimed to maximize net powermore »« less
Forward Modeling Dataset, protocol files, and forward modeling code (ResIPy)

Dataset Jamil, Ahsan

The files are final forward model simulations for four geophysical array configurations. Protocol files for each of the geophysical array and the forward model code (ResIPy) is included.
Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files

Dataset Jin, Wencheng ; Atkinson, Trevor A. ; Doughty, Christine ; ...

This data set includes the numerical modeling input files and output files used to synthesize data, and the reduced-order machine learning models trained from the synthesized data for reservoir thermal energy storage site identification. In this study, a machine-learning-assisted computational framework is presented to identify High-Temperature Reservoir Thermal Energy Storage (HT-RTES) site with optimal performance metrics by combining physics-based simulation with stochastic hydrogeologic formation and thermal energy storage operation parameters, artificial neural network regression of the simulation data, and genetic algorithm-enabled multi-objective optimization. A doublet well configuration with a layered (aquitard-aquifer-aquitard) generic reservoir is simulated for cases of continuous operationmore »« less
CCPP-ARM Parameterization Testbed Model Forecast Data

Dataset Klein, Stephen

Dataset contains the NCAR CAM3 (Collins et al., 2004) and GFDL AM2 (GFDL GAMDT, 2004) forecast data at locations close to the ARM research sites. These data are generated from a series of multi-day forecasts in which both CAM3 and AM2 are initialized at 00Z every day with the ECMWF reanalysis data (ERA-40), for the year 1997 and 2000 and initialized with both the NASA DAO Reanalyses and the NCEP GDAS data for the year 2004. The DOE CCPP-ARM Parameterization Testbed (CAPT) project assesses climate models using numerical weather prediction techniques in conjunction with high quality field measurements (e.g. ARMmore » data).« less
Model: Year-Long Reforecast, Forecast, Domain 02

Dataset Macduff, Matt

The primary purpose of WFIP2 Model Development Team is to improve existing numerical weather prediction models in a manner that leads to improved wind forecasts in regions of complex terrain. Improvements in the models will come through better understanding of the physics associated with the wind flow in and around the wind plant across a range of temporal and spatial scales, which will be gained through WFIP2’s observational field study and analysis.

Similar Records