Satellite Imaging to Revolutionise Australian Oil Spill Response
Australian scientists with CSIRO have improved the accuracy of detecting oil spills using satellite imagery in the hopes of preventing damage to marine environments.
Oil spills are devastating events which can irreparably damage the environment. Sometimes they happen despite best efforts, and sometimes they occur due to illegal dumping of materials into the ocean. However oil slicks are made, it is of vital importance that they are quickly discovered and cleaned up. One group of Australian scientists from CSIRO, (Australia’s national science agency), have researched improving the accuracy of using satellite imagery to detect these events so we can prevent damage to marine ecosystems, such as the Great Barrier Reef (GBR).
The GBR region in particular is recognised as a highly sensitive area by the Australian Maritime Safety Authority (AMSA) due to the high volume of ship traffic within the marine park (where ships could potentially discharge oil). Another high-risk area within Australian maritime borders is the North-West shelf off Western Australia, due to the operating oil and gas platforms.
“This research gives AMSA and other environmental agencies information that we haven’t had access to before. It could help us better assess regulatory compliance options and improve our ability to assess the extent of any oil spill. We will be able to respond in a more informed and cost-effective manner. It is all about reducing potential threats to the marine environment,” says Paul Irving, AMSA Senior Advisor, Science and Technical Response.
“This would be particularly helpful when conditions mean aircraft and ships cannot usefully be deployed to obtain the required intelligence imagery.”
An Australian First for Oil Spill Management
In a first of its kind project in Australian waters, CSIRO Coastal Ocean Colour and Radar Sensing Team have been using satellite imagery to improve the accuracy of detecting oil spills. A member of the team, David Blondeau-Patissier, explained in an interview with CSIRO, “Never before in Australia have Earth Observation techniques routinely been used to detect oil spills. However, over the last three years, we have developed an approach, in collaboration with the Department of Environment and Science (DES) Queensland and AMSA, to process all satellite imagery acquired over Australian waters by satellites from the European Space Agency Sentinel missions and analyse them for oil spills”.
Monitoring of the region is generally performed every 12 days using the Sentinel-1 satellite with approximately 80 images of the GBR (and extending through to Cape York) acquired over the course of the month. However, the processing of this earth observation data is computationally heavy, as the marine park spans an enormous 348,000 square kilometres - which is almost three times the length of the North-West Shelf in Western Australia.
Images from Space
Using satellite imagery allows a bird’s eye view of the ocean, making it easier to detect oil spills. For this project, Sentinel-1 SAR imagery was used to detect the presence of oil spills, and was found to far outperform the individual use of thermal and optical imagery. Initial assessments of the satellite imagery were complimented by secondary information to provide more accurate results.
This then allowed the development of techniques to use the Sentinel-1 imagery to detect oil spills. Thomas Schroeder, also a part of the research team, noted, “Using advances in high performance computing and machine learning, we are aiming to identify hot-spots of illegal discharges along a coastline, or oil platforms that regularly discharge oil more than others. This detection method can be vital for oil spill management response teams as it provides a map of the spill, independently of any weather or light conditions”.
The main source of imagery for this project was the Sentinel-1 SAR satellite, which is part of a new generation of satellites for Earth observation missions from the European Space Agency. The oil spill detection methods that have been developed because of the imagery from this satellite are looking to be applied to the NovaSAR-1 satellite, which was launched in 2018.
The next step of this project is to develop an algorithm using machine learning to fully automate the process of using satellite imagery to detect oil spills and apply this to alert systems to better protect marine environments.
Oil spills are not the only usage for this research, with the team also exploring use of the data for detection and monitoring of river runoff during the wet season, working side by side with other CSIRO water-quality programs like eReefs.
The new detection method can also be deployed rapidly across any region of the world, providing benefits not only to Australian maritime waters - but also in addition to Australia’s neighbours in South-East Asia or the Pacific Islands, where CSIRO research is currently underway.
For further information about this project, you can check out the report published by the CSIRO.