Empowerment for Volunteers Worldwide to Protect the Great Barrier Reef

Dell Technologies Deep Learning Empowers Volunteers Worldwide to Protect the Great Barrier Reef 

Dell Technologies announced today a new deep learning technology  model, launched in partnership with Australia-based conservation organisation Citizens of The Great  Barrier Reef, which will allow global citizen scientists to more quickly and accurately analyse  reconnaissance images collected from the Great Barrier Reef during the next phase of the Great Reef  Census (GRC). 

The new Dell deep learning model will better inform conservation efforts for the Great Barrier Reef,  one of the world’s greatest natural wonders. A previously implemented Dell edge solution deployed on  watercraft automatically uploads data directly to the deep learning model via a mobile network for  real-time image capture. This will enhance the capabilities of the GRC by speeding image analysis  that previously solely relied on human volunteers – allowing citizen scientists to support prompt  recovery efforts in areas that need it the most and during critical times of the year, such as the annual  spawning season. 

The deep learning analysis now takes less than one minute per photo, compared to seven or eight  minutes in previous census phases. While it took 1,516 hours to review 13,000 images in the first  GRC, the new model can analyse the same data set in less than 200 hours. 

The initiative aligns to Dell Technologies’ environmental, social and governance (ESG) ambitions to  advance sustainability, by creating technology that drives progress and working with customers,  partners, suppliers and communities to enable climate action. The GRC is a true partnership across  Asia Pacific and Japan (APJ) combining the expertise of the Citizens of the Great Barrier Reef team,  Dell, researchers from The University of Queensland (UQ) and James Cook University (JCU), Sahaj  Software Solutions and citizen scientists. Dell also worked with its data science team in Singapore to  continually refine and carry out extensive community testing of the selected deep learning model to  ensure that benchmarking standards were met.  

Looking ahead, Citizens of the Great Barrier Reef founder Andy Ridley hopes to expand the GRC,  powered by the Dell’s repeatable and scalable edge solution and deep learning model, to other reef  sites globally – with the first trial sites outside Australia to begin in Indonesia. 

Amit Midha, President, APJ and Global Digital Cities, Dell Technologies, said, “Dell Technologies  collaborates with like-minded organisations on ground to enable climate-positive societal impact. With  the Citizens of the Great Barrier Reef, our support for research using technology has come a long  way since the first Great Reef Census to today, where the power of deep learning will scale the  team’s conservation efforts to quick access of quality data and drive a successful collaboration  between all involved. We believe such innovations can help our partners make progress on their  sustainability ambitions and conservation efforts like these can be replicated both in APJ and  globally.” 

Key takeaways: 

• The ongoing collaboration with Citizens of the Great Barrier Reef supports Dell Technologies’  commitment to advancing sustainability and putting its purpose into action in APJ. • The new deep learning model by Dell enhances Great Barrier Reef conservation efforts by  reducing the time it takes to analyse reef images – volunteers can review 13,000 images in  just over a week with the new model; during the first Great Reef Census, this process took  more than two months. 

• In this year’s campaign, volunteers will analyse 42,000 images collected from 315 reefs along  the 2,300 km length of the reef marine park. 

• The deep learning semantic segmentation model is powered by a Dell high performance  computing (HPC) graphics processing unit (GPU) accelerated system to train the model and a  Dell PowerScale system to store the data. The onshore compute platform includes Dell  PowerEdge servers that support an AI training cluster and multiple AI inference engines.