AWS is no stranger to innovation. At the first re:Mars event in 2019, they showcased their work on some of the hottest topics in tech and science — machine learning, AI, robotics and space. This year in June 2022, they were back with even more exciting developments, including exci’s early wildfire detection system.
Powered by proprietary machine learning algorithms that analyse data from ground-based cameras and satellites for the presence of smoke and heat, this system could help prevent devastating wildfires like those we’ve seen in recent years. By leveraging AWS services, exci has been able to build an efficient wildfire detection platform that is processing over 2.5 million images and over 30GB of satellite data a day. It stores the images on Amazon S3.
exci employs deep machine learning to detect and predict wildfire locations by aggregating images, which are continuously built, trained, and deployed. Through the use of machine learning, exci can detect wildfire outbreaks and predict how they might spread, with a near-zero rate of false positives. This wildfire detection platform is then able to inform relevant authorities of potential wildfires within three minutes of smoke detection, which could help save lives and property.
Christopher Tylor, the managing director of exci said:” Trusting AWS to manage exci’s core infrastructure, we do not have to worry about the management and administration of its platform and backend operations. Our architecture on AWS allows us to process one billion images per year. Thanks to the efficiency of the AWS team, who is always on top of things, we can focus on other areas of the business, such as improving customer service, expanding the company, and working towards protecting communities from harm.”
by Gabrielle Tylor
20 October 2022