Intel has recently partnered with Accenture and the Sulubaaï Environmental Foundation to create an AI-driven data collection platform aimed at analyzing and protecting vulnerable marine habitats, habitats like coral reefs.
A combination of climate change, pollution, and overfishing have been damaging the world’s oceans, particularly coral reefs. Coral reefs around the world are experiencing mass die-offs and problems like coral bleaching. Scientists and conservationists are looking for ways to protect coral reefs and help them recover. Designing plans to support coral reefs requires data, and as Engadget reported, Intel has partnered with two environmental foundations to create the CORaiL platform. The purpose of CORaiL will be collecting information on coral reefs and other marine habitats, providing researchers with the data they need to determine what strategies could be effective at protecting vulnerable marine ecosystems. As Jason Michell, managing director of the Communications, Media, and Technology practice at Accenture explained in a blog post:
“Artificial intelligence provides unprecedented opportunities to solve some of society’s most vexing problems. Our ecosystem of corporate and social partners for this ‘AI for social good’ project proves that there is strength in numbers to make a positive environmental impact.”
In May of last year, the team of researchers and engineers from the three organizations installed concrete structures along reefs found near the Philippines’ Pangatalan Island. The concrete chunks contained sections of living coral capable of growing into new habitat for creatures inhabiting coral ecosystems. In addition, the researchers placed video cameras underwater near the structures so they could collect data on the coral and the surrounding environment. The cameras utilized an AI-driven video analytics system developed by Accenture, and the cameras enabled the researchers to gather data on the reefs through minimally invasive methods.
Accenture’s AI video analytics system lets researchers collect real-time video data from the coral environments, without needing to be physically present in the water. While many divers collect footage of coral reefs, this incurs travel expenses and presents the possibility that the divers could interfere with wildlife in the area. The AI video platform does much of the data collection and analysis for the research teams, continually monitoring the environment for change, and letting researchers do analysis in more or less real-time.
Over the course of the past year, CORaiL has collected around 40,000 images for analysis, and the images are already helping researchers analyze how coral reefs change in response to shifting environmental conditions. Meanwhile, engineers from the cooperative effort are already working on the next generation of the CORaiL system. The next proptype will include a backup power supply and an optimized series of convolutional neural networks. New versions of CORaiL might be employed for tasks other than studying coral, such as studying how tropical fish migrate through cold waters or monitoring for violators of reef protection orders.
CORaiL isn’t the only new project to make use of AI with the goal of protecting the oceans. A new AI system designed by researchers from the Plymouth Marine Laboratory in the UK tracks plastic pollution in the ocean through the analysis of satellite imagery. The AI system analyzes imagery collected by the European Space Agency’s (ESA) satellites and finds large chunks of floating debris by analyzing the “spectral signature” produced by the trash (patterns of light absorbed and reflected by the trash). After training, the AI was able to recognize a multitude of different objects when tested on images of seas from Vietnam, Canada, Ghana, and Scotland. The AI reportedly achieved approximately 86% accuracy when differentiating trash from natural objects.
According to the scientists involved in the research, their experiment marks the first time that plastic pollution has been tracked with satellites. The research team wants to improve the technique and enable it to detect patches of trash within rivers and along coastal regions.
- How VCs Can Identify High Potential Investments Using Artificial Intelligence
- Brain Machine Interface Types Mental Handwriting
- Neural Rendering: How Low Can You Go In Terms Of Input?
- Researchers Simulate Movement of Single-Celled Organisms
- Determining The Extent Of Video Surveillance Through Google Street View Data