Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak
The submission includes the labeled datasets, as ESRI Grid files (.gri, .grd) used for training and classification results for our machine leaning model:
- brady_som_output.gri, brady_som_output.grd, brady_som_output.*
- desert_som_output.gri, desert_som_output.grd, desert_som_output.*
The data corresponds to two sites: Brady Hot Springs and Desert Peak, both located near Fallon, NV.
Input layers include:
- Geothermal: Labeled data (0: Non-geothermal; 1: Geothermal)
- Minerals: Hydrothermal mineral alterations, as a result of spectral analysis using Chalcedony, Kaolinite, Gypsum, Hematite and Epsomite
- Temperature: Land surface temperature (% of times a pixel was classified as "Hot" by K-Means)
- Faults: Fault density with a 300mradius
- Subsidence: PSInSAR results showing subsidence displacement of more than 5mm
- Uplift: PSInSAR results showing subsidence displacement of more than 5mm
Also, the results of the classification using Brady and Desert Peak to build 2 Convolutional Neural Networks. These were applied to the training site as well as the other site, the results are in GeoTiff format.
- brady_classification: Results of classification of the Brady-trained model
- desert_classification: Results of classification of the Desert Peak-trained model
- b2d_classification: Results of classification of Desert Peak using the Brady-trained model
- d2b_classification: Results of classification of Brady using the Desert Peak-trained model
Citation Formats
Colorado School of Mines. (2020). Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak [data set]. Retrieved from https://dx.doi.org/10.15121/1773692.
Moraga, Jim, Cavur, Mahmut, Duzgun, H. Sebnem, and Soydan, Hilal. Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak. United States: N.p., 01 Sep, 2020. Web. doi: 10.15121/1773692.
Moraga, Jim, Cavur, Mahmut, Duzgun, H. Sebnem, & Soydan, Hilal. Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak. United States. https://dx.doi.org/10.15121/1773692
Moraga, Jim, Cavur, Mahmut, Duzgun, H. Sebnem, and Soydan, Hilal. 2020. "Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak". United States. https://dx.doi.org/10.15121/1773692. https://gdr.openei.org/submissions/1288.
@div{oedi_1288, title = {Training dataset and results for geothermal exploration artificial intelligence, applied to Brady Hot Springs and Desert Peak}, author = {Moraga, Jim, Cavur, Mahmut, Duzgun, H. Sebnem, and Soydan, Hilal.}, abstractNote = {The submission includes the labeled datasets, as ESRI Grid files (.gri, .grd) used for training and classification results for our machine leaning model:
- brady_som_output.gri, brady_som_output.grd, brady_som_output.*
- desert_som_output.gri, desert_som_output.grd, desert_som_output.*
The data corresponds to two sites: Brady Hot Springs and Desert Peak, both located near Fallon, NV.
Input layers include:
- Geothermal: Labeled data (0: Non-geothermal; 1: Geothermal)
- Minerals: Hydrothermal mineral alterations, as a result of spectral analysis using Chalcedony, Kaolinite, Gypsum, Hematite and Epsomite
- Temperature: Land surface temperature (% of times a pixel was classified as "Hot" by K-Means)
- Faults: Fault density with a 300mradius
- Subsidence: PSInSAR results showing subsidence displacement of more than 5mm
- Uplift: PSInSAR results showing subsidence displacement of more than 5mm
Also, the results of the classification using Brady and Desert Peak to build 2 Convolutional Neural Networks. These were applied to the training site as well as the other site, the results are in GeoTiff format.
- brady_classification: Results of classification of the Brady-trained model
- desert_classification: Results of classification of the Desert Peak-trained model
- b2d_classification: Results of classification of Desert Peak using the Brady-trained model
- d2b_classification: Results of classification of Brady using the Desert Peak-trained model}, doi = {10.15121/1773692}, url = {https://gdr.openei.org/submissions/1288}, journal = {}, number = , volume = , place = {United States}, year = {2020}, month = {09}}
https://dx.doi.org/10.15121/1773692
Details
Data from Sep 1, 2020
Last updated May 17, 2021
Submitted Feb 19, 2021
Organization
Colorado School of Mines
Contact
Jim Moraga
303.273.3768
Authors
Keywords
geothermal, energy, geothermal exploration, hydrothermal mineral alterations, land surface temperature, fault density, PSInSAR, Subsidence, Uplift, Brady Hot Springs, Desert Peak, Nevada, convolutional neural network, Fallon, machine learning, model, hydrothermal, mineral, temperature, raster, geospatial data, GeoTIFFDOE Project Details
Project Name Detection of Potential Geothermal Exploration Sites from Hyperspectral Images via Deep Learning
Project Lead Mike Weathers
Project Number EE0008760
