Optimising vegetation management and grazing in solar farms
Supervisory team details
University
| Name of university supervisor | Sara Deilami |
| Name of university | Macquarie University |
| Email address | sara.deilami@mq.edu.au |
| Faculty | Faculty of Science and Engineering |
CSIRO
| Name of CSIRO supervisor | Sahan Kuruneru Cindy Ong |
| Email address | Sahan.Kuruneru@csiro.au Cindy.Ong@csiro.au |
| CSIRO Business Unit | Energy |
Industry
| Name of industry supervisor | Mona Janbaz |
| Name of business/organisation | ACEN Renewables |
| Email address | mona.janbaz@acenrenewables.com.au |
| Website | www.acenrenewables.com.au |
Project details
| Project title | Optimising vegetation management and grazing in solar farms utilising high resolution aerial image processing |
| Project description | This project aims to use high spatial, spectral and temporal resolution satellite images and artificial intelligence to derive measurements that enhance vegetation management and grazing efficiency in solar farms. The expected outcome is to develop algorithms that can be applied to near real-time satellite data to enable the spatially comprehensive measurements of vegetation growth, grazing patterns overgrazing, curing rating for decision making in monitoring and determining the effectiveness of land management strategies. The student will use historical and current ground-based data and observations to train a machine learning model to derive the measurements from the satellite imagery. The model will also be validated with another set of independent ground-based data. The potential benefits of these satellite-derived measurements are enhanced vegetation management efficiency, bush fire risk monitoring and grazing resulting in improved solar farm operation. Main objectives: Develop experiments to collect field training and validation data that can be associated with concurrent satellite data. Investigate a range of available satellite imagery, including free and commercial data, to determine the most appropriate technology for the application, including determining the acceptable degree of accuracy and uncertainty. Develop algorithms using the most appropriate satellite imagery to monitor and predict key factors including curing rates, vegetation growth, grazing patterns that can be used to determine the effectiveness of land management. Validate the satellite-derived measurements with real- world data. Deliverables: Advanced Algorithms to produce or derive curing ratio, vegetation growth and grazing patterns from satellite imagery. Multi-temporal satellite-derived maps of curing ratio and vegetation growth which may be used to improve fire management and determine grazing patterns. Case history demonstrating the use of satellite derived data for improving vegetation management, optimise grazing patterns, prevent overgrazing, and fire management. This Project scope may be modified during the Term as agreed in writing between all parties. |
| Primary location of student | Macquarie University, Balaclava Road, North Ryde NSW. |
| Industry engagement component location | ACEN Australia, Suite 25.02, Level 25, 25 Bligh St, Sydney, NSW. |
| Other locations | CSIRO Clayton, Research Way, Clayton VIC 3168, Australia and CSIRO Kensington, 26 Dick Perry Avenue, Kensington WA. |
| Ideal student skillset | Essential Background in spatial sciences, remote sensing, GIS, physics, engineering, mathematics or data analytics with skills and experience in AI algorithm development, programming languages (such as Python), remote sensing image processing and analysis. Desirable Good communication skills. Experience in agriculture or environmental management. Experience in working with instrumentation in the field. Knowledge of infrared spectroscopy. |
| Application Close Date | Open until position filled |
Previous post:
Coming up next:
End of list