Programs and Code for Geothermal Exploration Artificial Intelligence
The scripts below are used to run the Geothermal Exploration Artificial Intelligence developed within the "Detection of Potential Geothermal Exploration Sites from Hyperspectral Images via Deep Learning" project. It includes all scripts for pre-processing and processing, including:
- Land Surface Temperature K-Means classifier
- Labeling AI using Self Organizing Maps (SOM)
- Post-processing for Permanent Scatterer InSAR (PSInSAR) analysis with SOM
- Mineral marker summarizing
- Artificial Intelligence (AI) Data splitting: creates data set from a single raster file
- Artificial Intelligence Model: creates AI from a single data set, after splitting in Train, Validation and Test subsets
- AI Mapper: creates a classification map based on a raster file
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[
"019:20"
]
|
| contactPoint |
{
"fn": "Jim Moraga",
"@type": "vcard:Contact",
"hasEmail": "mailto:jmoraga@mines.edu"
}
|
| dataQuality |
true
|
| description | The scripts below are used to run the Geothermal Exploration Artificial Intelligence developed within the "Detection of Potential Geothermal Exploration Sites from Hyperspectral Images via Deep Learning" project. It includes all scripts for pre-processing and processing, including: - Land Surface Temperature K-Means classifier - Labeling AI using Self Organizing Maps (SOM) - Post-processing for Permanent Scatterer InSAR (PSInSAR) analysis with SOM - Mineral marker summarizing - Artificial Intelligence (AI) Data splitting: creates data set from a single raster file - Artificial Intelligence Model: creates AI from a single data set, after splitting in Train, Validation and Test subsets - AI Mapper: creates a classification map based on a raster file |
| distribution |
[
{
"@type": "dcat:Distribution",
"title": "README.md",
"format": "md",
"accessURL": "https://gdr.openei.org/files/1307/README.md",
"mediaType": "application/octet-stream",
"description": "README for the Geothermal AI. Provides a guide on how to properly run the provided code in this submission."
},
{
"@type": "dcat:Distribution",
"title": "Create DOE Dataset.py",
"format": "py",
"accessURL": "https://gdr.openei.org/files/1307/create_doe_dataset.py",
"mediaType": "application/octet-stream",
"description": "Creates the data set for the Geo AI. More information of this code can be found in the README within this submission."
},
{
"@type": "dcat:Distribution",
"title": "Displacement SOM R Scripts.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/displacement_som_r_scripts.zip",
"mediaType": "application/zip",
"description": "Post-processing for PSInSAR analysis with SOM
R scripts that use the CVS output from Sarproz to generate SOM-ready data (by cropping data and recalculating slopes), and later classifies the data using Self Organizing Maps (SOM).
Must be run in order:
01_psi_to_som.R
02_displacement_som.R
Additional documentation in Roxygen format within each file.
"
},
{
"@type": "dcat:Distribution",
"title": "DOE ANN.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/doe-ann.zip",
"mediaType": "application/zip",
"description": "Python and Shell (SLURM) scripts to create a dataset, build an AI and map using the created AI. It requires Python 3, TensorFlow 2.4, and a machine with one or multiple GPUs"
},
{
"@type": "dcat:Distribution",
"title": "DOE ANN Map.py",
"format": "py",
"accessURL": "https://gdr.openei.org/files/1307/doe_ann_map.py",
"mediaType": "application/octet-stream",
"description": "Maps the classification from a raster image using a trained AI model. Requires Python 3 and multiple Python software packages such as NumPy and OSGeo."
},
{
"@type": "dcat:Distribution",
"title": "DOE GeoAI.py",
"format": "py",
"accessURL": "https://gdr.openei.org/files/1307/doe_geoai.py",
"mediaType": "application/octet-stream",
"description": "Creates a Geothermal AI model from labeled data. This is the main program to create, train and use an ANN to classify regions based on geothermal potential. Requires Python 3 and multiple Python software packages."
},
{
"@type": "dcat:Distribution",
"title": "DOE TIFF.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/doe_tiff.zip",
"mediaType": "application/zip",
"description": "Libraries to be used with the Geothermal AI and related python scripts."
},
{
"@type": "dcat:Distribution",
"title": "LST Extract.sh",
"format": "sh",
"accessURL": "https://gdr.openei.org/files/1307/lst_extract.sh",
"mediaType": "application/octet-stream",
"description": "Shell script to extract relevant files from a directory with Landsat 8 ADR LST compressed files."
},
{
"@type": "dcat:Distribution",
"title": "LST R Scripts.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/lst_r_scripts.zip",
"mediaType": "application/zip",
"description": "Land Surface Temperature K-Means Classifier
R scripts to extract data, classify through K-Means and save final result for Land Surface Temperature anomalies (hot areas) from Landsat ADR LST data."
},
{
"@type": "dcat:Distribution",
"title": "Mineral Markers.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/mineral_markers.zip",
"mediaType": "application/zip",
"description": "Mineral marker summarizing R scripts to summarize the outputs from ENVI target detection for further data fusion. Outputs the results of CEM, SAM, ACE, MF, MTMF, OSP, TCIMF, TCIMF and MTTCIMF.
Also, shows automatic clustering results using several algorithms ( "IJDefault", "Intermodes", "IsoData", "Minimum", "Moments", "Otsu", "RenyiEntropy") to obtain cutoff thresholds for the anomaly detectors."
},
{
"@type": "dcat:Distribution",
"title": "Sbatch Scripts.zip",
"format": "zip",
"accessURL": "https://gdr.openei.org/files/1307/sbatch_scripts.zip",
"mediaType": "application/zip",
"description": "Compressed directory with scripts to to be used to run the Geothermal AI and related python scripts in an HPC environment with SLURM."
}
]
|
| DOI | 10.15121/1787330 |
| identifier | https://data.openei.org/submissions/7425 |
| issued | 2021-04-27T06:00:00Z |
| keyword |
[
"AI",
"Geothermal AI",
"K-Means",
"LST",
"Landsat ADR LST",
"Machine Learning",
"NumPy",
"Python",
"R",
"SLURM",
"Self Organizing Map",
"Shell",
"Shell scripts",
"TensorFlow",
"anomaly detection",
"artificial intelligence",
"blind",
"code",
"deep learning",
"energy",
"exploration",
"geothermal",
"geothermal exploration",
"k mean",
"land surface temperature",
"raster",
"remote sensing",
"sbatch",
"site detection"
]
|
| landingPage | https://gdr.openei.org/submissions/1307 |
| license | https://creativecommons.org/licenses/by/4.0/ |
| modified | 2021-06-09T21:22:13Z |
| programCode |
[
"019:006"
]
|
| projectLead | Mike Weathers |
| projectNumber | EE0008760 |
| projectTitle | Detection of Potential Geothermal Exploration Sites from Hyperspectral Images via Deep Learning |
| publisher |
{
"name": "Colorado School of Mines",
"@type": "org:Organization"
}
|
| spatial |
"{"type":"Polygon","coordinates":[[[-119.9582078125,32.71358983108084],[-112.8941,32.71358983108084],[-112.8941,40.47558089276303],[-119.9582078125,40.47558089276303],[-119.9582078125,32.71358983108084]]]}"
|
| title | Programs and Code for Geothermal Exploration Artificial Intelligence |
