Clean Energy Capability Portfolio | Storage Technologies |
Energy and Mineral Exploration
Machine learning can help unlock the secrets contained in vast amounts of geoscientific data about the subsurface for resources extraction , civil and environmental engineering , and the application of emerging technologies , such as underground hydrogen storage and CO2 geosequestration . |
Competitive Advantage • Machine learning techniques can build subsurface models in minutes , rather than weeks
• Greater accuracy in analysis using all available data to create models
• Expertise in the optimisation of infrastructure placement
Impact • Reduced expenses and environmental impact in the collection of data , extraction or storage of energy resources , and the placement of facilities and infrastructure
• More accurate mapping of subsurface geology
• Reducing the labour-intensity required in the interpretation process
Successful Applications |
Capabilities and Facilities • Evaluation of frontier basin properties and energy or storage potential , especially where little data currently exists
• Software for automated interpretation of seismic data
Our Collaborators • Lundin Norway
• SoluForce
• Department of Climate Change , Energy , Environment and Water ( DCEEW )
• Geoscience Australia
• CO2CRC
• EXIGE
• Santos
• Kumul Petroleum
|
• Automated interpretation of complex seismic datasets from the environmentally sensitive Barents Sea region in the Arctic
• Constraining the timing of major basin evolutionary processes in several basins , including the North West Shelf and South Nicholson Basin , Australia , Siberia , East Africa , the Caribbean , and the Scotia Sea
|
• CSIRO Mineral Resources
More Information Dr Stuart Clark Minerals and Energy Resources Engineering T : + 61 468 332 796
|
||
E : stuart . clark @ unsw . edu . au |
|||
78 |