Tracking of a key environmental transition indicator to help municipalities, industrial facilities, and farms make informed decisions
Today’s air quality monitoring systems only provide an indeterminate total particle count. Ōberon Sciences’ solution goes further with real-time measurement and identification of particle sources, giving public- and private-sector stakeholders actionable information.
The device provides real-time data on the nature of particles present in the air. Credit: Oberon
Ōberon Sciences’ Aerōtape leverages a patented technology to provide precision real-time data not only on the number of particles, but on the exact kind of particles in the air. The suspended particles in the air are captured and pictured under different lightings. The resulting data is processed by AI algorithms to determine the types of particles and particle counts.
Monitoring data on traffic-related pollution, pollen, mold and other particles can then be used by urban planners and other stakeholders. Factories that emit dust plumes can take more targeted corrective action sooner, preventing unnecessary pollution, for example. This data can also help air quality monitoring bodies determine why pollution thresholds have been exceeded and respond more effectively.
The company’s digital business model is built around services like supervision interfaces that display the data produced by the instruments.
So far Ōberon Sciences has bootstrapped its development through sales revenue and research grants. The company plans to raise equity and ramp up its partnerships with academic research labs to accelerate sales and R&D.
Key figure: 5 minutes
Unlike current solutions based on asynchronous chemical analysis, Ōberon Sciences provides information on which pollutants are present every 5 minutes.
KEY Markets:
- Urban development: construction sites and road monitoring, monitoring of invasive plant species
- Industry: emissions monitoring, dust plume mitigation, crisis management
- Air monitoring: pollution monitoring by source
Technologies used:
- Microscope imaging
- Machine learning
Year founded: 2021
CEA Institute: CEA-Lsce