At its Ignite conference, Microsoft announced today that Premonition, a robotics and sensor platform for monitoring and sampling disease carriers such as mosquitoes and a cloud-based software stack for analyzing samples, will soon be previewing private.
The idea here, as Microsoft describes it, is to set up a system that can basically function as a weather monitoring system, but for epidemics. The company first introduced the project in 2015, but it has come a long way since then.
Premonition sounds like a pretty wild project, but Microsoft says it’s based on five years of R&D in this area. Company says it’s partnering with National Science Foundation Convergence Acceleration Program and academic partners such as Johns Hopkins University, Vanderbilt University, the University of Pittsburgh and the Institute for Health Metrics and Evaluation at the University of Washington to test the tools it is developing here. In addition, it is also working with pharmaceutical giant Bayer to “develop a deeper understanding of vector-borne diseases and the role of autonomous sensor networks for the detection of biotherapies”.
Currently, it appears the focus is on mosquito-borne diseases and Microsoft has in fact set up a “ premonitory proving ground ” at its Redmon campus to help researchers test their robots, to train their machine learning models and analyze the data they collect. In this level 2 arthropod containment facility, the company can breed and analyze mosquitoes. But the idea is to go way beyond and monitor the entire biome.
So far, according to Microsoft, the Premonition system has analyzed more than 80 trillion base pairs of genomic material for biological threats.
“About five years ago, we saw robotics, artificial intelligence, and cloud computing reaching a tipping point where we could monitor the biome in entirely new ways, on entirely new scales,” said Ethan Jackson. , Senior Director of Premonition, in a video. the company released today. “It was really the 2014 Ebola epidemic that led to this awareness. How did one of the rarest viruses on the planet go from animal to human to cause this epidemic? What signals are we missing that could have allowed us to predict it? “
Two years later, in 2016, when Zika first appeared, the team had already built a small fleet of smart robotic traps capable of autonomously identifying and capturing mosquitoes. The system identifies the mosquito and can then decide in a fraction of a second whether to capture it or let it fly. In just one night, Jackson said, the trap has already been able to identify up to 10,000 mosquitoes.
In the United States, the first place Microsoft deployed these systems was in Harris County, Texas.
“Everything we do now in terms of treating mosquitoes is reactive – we’re seeing a lot of mosquitoes, we’re going to spray a lot of mosquitoes,” said Douglas E. Norris, entomologist and professor of molecular microbiology and immunology at the Johns Hopkins University, which was part of this project. “Imagine if you had a forecasting system that shows, in a few days, you’re going to have a lot of mosquitoes based on all this data and these patterns – then you could go out and deal with them sooner before they bite, spray, hit. – early so as not to have these large proliferation of mosquitoes which could then lead to the transmission of diseases. “
It is, by all means, a very ambitious project. Why is Microsoft announcing it now, at its Ignite conference? Unsurprisingly, the entire system relies on the Microsoft Azure cloud to provide the storage and computing power to run – and it’s a good way for Microsoft to show off its AI systems as well.