GeoThermalCloud.jl: Machine Learning framework for Geothermal Exploration

GeoThermalCloud.jl is a repository containing all the data and codes required to demonstrate applications of machine learning methods for geothermal exploration.

GeoThermalCloud.jl includes:

site data
simulation scripts
jupyter notebooks
intermediate results
code outputs
summary figures
readme markdown files

GeoThermalCloud.jl showcases the machine learning analyses performed for the following geothermal sites:

Brady: geothermal exploration of the Brady geothermal site, Nevada
SWNM: geothermal exploration of the Southwest New Mexico (SWNM) region
GreatBasin: geothermal exploration of the Great Basin region

Reports, research papers, and presentations summarizing these machine learning analyses are also available and will be posted soon.

Julia installation

GeoThermalCloud Machine Learning analyses are performed using Julia.

To install the most recent version of Julia, follow the instructions at https://julialang.org/downloads/

GeoThermalCloud installation

To install all required the modules, execute in the Julia REPL:

import Pkg
Pkg.add("GeoThermalCloud")

GeoThermalCloud examples

GeoThermalCloud machine learning analyses can be executed as follows:

import Pkg
Pkg.add("GeoThermalCloud")
import GeoThermalCloud

GeoThermalCloud.SWNM() # performs analyses of the Sounthwest New Mexico region
GeoThermalCloud.GreatBasin() # performs analyses of the Great Basin region
GeoThermalCloud.Brady() # performs analyses of the Brady site, Nevada

GeoThermalCloud machine learning analyses can be also executed as Jupyter notebooks as well

GeoThermalCloud.notebooks() # open Jupyter notebook to acccess all GeoThermalCloud notebooks
GeoThermalCloud.SWNM(notebook=true) # opens Jupyter notebook for analyses of the Sounthwest New Mexico region
GeoThermalCloud.GreatBasin(notebook=true) # opens Jupyter notebook for analyses of the Great Basin region
GeoThermalCloud.Brady(notebook=true) # opens Jupyter notebook for analyses of the Brady site, Nevada

SmartTensors

GeoThermalCloud analyses are performed using the SmartTensors machine learning framework.

SmartTensors provides tools for Unsupervised and Physics-Informed Machine Learning.

More information about SmartTensors can be found at smarttensors.github.io and tensors.lanl.gov.

SmartTensors includes a series of modules. Key modules are:

NMFk: Nonnegative Matrix Factorization + k-means clustering
NTFk: Nonnegative Tensor Factorization + k-means clustering