The Great Barrier Reef stretches 2,300 km with about 3000 reefs. Because of its enormity, monitoring has become a challenge.
However, a researcher from the Queensland University of Technology, who is using drones and artificial intelligence (AI) to monitor its health, has received backing from a software giant as part of the company’s US$ 50 million AI for Earth program.
As reported, the grant will allow the researcher to quickly process data of the reef using cloud computing services, saving weeks or perhaps months in data crunching time.
Professor Gonzalez, in partnership with the Australian Institute of Marine Science (AIMS), has captured data from drones that are flying at 60m above the Great Barrier Reef at vulnerable reef locations.
Drone, AI and Cloud working together
The drone system uses specialised hyperspectral camera which, when validated using underwater data from AIMS, can not only identify coral against the background of sand and algae but can also determine the type of coral and precise levels of coral bleaching.
A standard camera detects images in three bands of the visible spectrum of red, green and blue.
The hyperspectral camera, meanwhile, uses 270 bands of the visible and near-infrared spectrum while flying over the reef.
Studying the health of the reef using drones began two years ago and the challenge was in processing the huge amounts of data the drones captured.
It is time consuming to process Gigabyte worth of hyperspectral imagery. On a regular desktop PC, for instance, processing the data will take months.
There is really a need to scale up. With the help of cloud services and tools, this can be done within days or hours for the smaller reefs.
Since the first flight project 18 months ago, in which the drones were used to analyse the health of four coral reefs, the Professor has processed about 30% of the data the drones collected.
The rest of the data can now be quickly processed with the help of the grant.
Reef monitoring program
The drones have already proven to be successful tool in reef monitoring.
It is capable of covering a bigger area in a day as compared to in-water services. Moreover, its coverage is not hampered by clouds, which is the usual problem with surveys done by plane or satellite.
Add to that the level of resolution that drones have as compared to either satellite or aircraft.
With the reef monitoring program, the Professor benchmarked the drone system by using data from AIMS divers that identified coral types and the health of coral species marked on a graded scale.
Processing all of the data from the first drone study of the Great Barrier Reef is just the first step in what would be an ongoing monitoring program.
Working with AIMS researchers allowed them to do follow-up analysis of the same area to calculate changes in the reef’s condition.
AI to save the Earth
The company’s AI for Earth program is designed to use technology to help mitigate and adapt to challenges such as climate change and the catastrophic loss of biodiversity.
The world is seeing rapid advancements in cloud and AI solutions that are unlocking new possibilities to solve the world’s most challenging problems.
Time is too short and current human resources are too few to solve urgent climate related challenges without the exponential power of AI.
By putting AI in the hands of researchers and organisations, important data insights can be used to help solve issues related to water, agriculture, biodiversity and climate change.