Data Fusion and Machine Learning
- $1.87m Funded by ARENA
- $6.59m Total project cost
Summary
The resulting information and software can be used to improve exploration, discovery and characterisation methods for targeted geothermal exploration.
Need
Geoscience Australia estimates that 1% of Australia’s geothermal energy could supply the nation’s annual requirements for 26,000 years.
Geothermal energy is based on the tapping of heat (or thermal) energy from rocks and water deep beneath the earth’s surface. It has the potential to be a viable energy solution for Australia as it is abundant and renewable, has a relatively low environmental footprint, and is a source of constant energy.
The aim of geothermal exploration and discovery is to determine where the best future sources of geothermal energy (or target sites) are located. This is of particular interest because exploration data is expensive and information sources are sparse.
Learn more
Report: Data Fusion & Machine Learning for Geothermal Target Exploration & Characterisation Software Code
This open source software code enables the user to build on the IT research developed through the project that takes geothermal data from a wide variety of sources and uses modern statistical methods to analyse the data for targeted geothermal exploration.
Report: Geoportal – Data Fusion and Machine Learning for Geothermal Target Exploration and Characterisation Tool
This tool enables the user to build on the IT research that takes geothermal data from a wide variety of sources and uses modern statistical methods to analyse the data to assist with targeted geothermal exploration.
Report: Geothermal Subterranean Data Portal Calculations
A report on an algorithm for quantifying the inherent uncertainty in the geothermal exploration problem enabling geothermal investors and developers reason about the risk of taking a certain action or the value of financing a particular survey.
Project innovation
The project used geothermal data from a wide variety of sources and applied modern statistical methods to analyse the data. The resulting information and software, ‘Obsidian’, can be used to reduce the uncertainties associated with exploration, discovery and characterisation methods for targeted geothermal exploration.
Obsidian enables better identification of target sites’ properties (such as porosity, stress regime, fracture susceptibility, fault geometry and compliance) to determine the probability that a site has the properties favourable for the production of geothermal energy,
The project’s information and software can also be used to improve exploration to find potential Engineered Geothermal Systems (EGS) targets while causing a minimum impact to the environment, which is a high priority.
Benefit
The project has the potential to meet the geothermal industry’s urgent need to access more information from existing data in order to better define potential targets, which will help reduce the risks and costs of geothermal exploration.
