Researchers will now use the power of technologies to monitor and help protect the Great Barrier Reef. Following the photographs taken by citizen scientists, Artificial Intelligence (AI) and deep learning will be used.
Citizens of the Great Barrier Reef recruited boats to help survey over 300 reefs from the tip of Queensland down to Lady Elliot Island in 2020 and early this year, according to ABC. They were able to take 52,000 photos of the reef to see the big picture in regards of its health. They were then asked to help identify problem areas, such as bleach to target better restoration efforts.
Dell has developed a new AI system that will see around 13,000 reef images analyzed a week or approximately one minute per photo. While the Singapore-based data science team worked with universities to develop the Great Reef Census (GRC) technology to identify five crucial coral categories in every image.
The analyzed data will be shared with University of Queensland and James Cook University researchers for better prioritization of reef conservation efforts when the program goes live.
A previously implemented Dell edge solution deployed on watercraft was able to upload data automatically to the deep learning model through a mobile network for real-time image capture. With this, it will enhance the capabilities of the Great Reef Census as it speeds up image analysis. Also, the new model will be able to analyze the same data set in less than 200 hours.
The initiative aligns Dell's Environmental, Social and Governance (ESG) ambitions to boost sustainability through the creation of technology that drives progress, and working with partners, customers, suppliers, and communities to promote climate action.
According to BW Businessworld, Dell has developed the model for GRC over the last five months by model by prioritizing core categories, understanding the dataset, cleaning the dataset, and building hundreds of models with different model architectures and hyperparameters.
"This deep learning still relies on human input: someone of the reef takes a photo, and the deep learning model defines the coral outline and health status; then, someone else can check the outline and confirm the label before the data is sent to the University of Queensland," said Aruna Kolluru, the Chief Technologist, Emerging Technology, Dell technologies, Asia Pacific and Japan.
Over the past 30 years, the Great Barrier Reef has been hit with mass bleaching. Based on the current rate, the Great Barrier Reef is facing an extinction of coral. The Great Barrier Reef could have passed the point of no return and could be on track to disappear in as little as 50 years. With this latest technologies, we could save it.
This article is owned by Tech Times.
Written by: April Fowell
