IBM AI Helps Australia Solve the Depleting Coastline Problem

Australia’s outstretched coastlines are in danger from their own waters. The country has more than 10,000 beaches, that are becoming deplete. The huge waves of water rising from the sea are eating away its coastlines. Investments by Gold Coast Council for up to $14 million has already been made to restore the coastlines.

Scientists and researchers opine, prevention may cost a lot more than rehabilitation of these beaches and increasing their coastal boundaries, sands of which are now being swallowed by waters. Seagrass could save that from happening but the process of locating, procuring and testing seagrass is lengthy and time consuming, which is where, IBM devised AI comes in the picture.

IBM’s hybrid cloud approach to AI on the IBM Power Systems AC922 using IBM Watson Machine Learning Accelerator Community Edition, may help Australian coastlines, with data collection and labeling work for testing and identification of seagrass, moving at inhuman speed, saving labor, effort and time. Seagrass meadow formations can safeguard the beaches, but the process at human pace could take more than 50 years. The footage manually taken, due to its scattered availability, takes days. Once the data is taken, it needs to be compiled, categorized and selected, deeming suitability for seagrass testing.

“Really just a processing platform, they have no visualization, they have no data storage … and they effectively just store everything by sending each other emails,” he explained. “Not a very scalable or usable platform. And It also takes them an enormous amount of effort to do this labelling — five hours for a 10-hour video, “said IBM Systems Data Scientist Dr Adam Makarucha told the Gartner Application Architecture, Development, and Integration Summit in Sydney. There are remaining 500 hours of more footage to be assessed.

IBM stepped in with its AI, taking care of this arduous mapping process. “The over 500 hours of existing footage they have, well this system could process it in less than a day, in comparison to 10 person days. And If you extrapolate that 10 person days into actual work days, that’s six and a half weeks of somebody constantly labelling seagrass,” Makarucha said.

He further added, “The benefits of a private cloud infrastructure is that we can get very specific compute very fast and high performance for accelerating these training jobs. I think the most important thing is that you want to do your training where your data lives, and in this case, our data lives in the private cloud infrastructure.”