Air Quality Station
Cities are demanding reference Air Quality Stations that have high costs to monitor key pollution parameters. Libelium solves this by providing smarter, smaller and more affordable Air Quality Stations that collect and analyse data through Libelium Cloud using Artificial Intelligence.
- Gases, particle matter, noise level and weather station
- Radio: LTE (4G)
- Machine learning algorithms applied
The Air Quality Station will allow your city to monitor key pollution parameters through Artificial Intelligence
More granularity to measure AQI in the city
Cities require Reference Air Quality stations to monitor key pollution parameters. These stations have high costs and their size is significant.
A higher spatial granularity is needed with a much larger number of reference stations spread throughout the city.
Libelium can solve this by providing smarter Air Quality Stations that can be distributed in the key points of the smart city.
AQI measurement solution
The new Air Quality Station has been designed to integrate Artificial Intelligence to create predictive models that you can manage through Libelium Cloud.
1. Parameters that can be measured
Air Quality Station allows you to measure the most relevant pollutants and key parameters required in every air quality project.
- Particulate matter (PM2.5, PM10)
- Different gases: CO, NO2, NO, O3, SO2
- Weather Station: Wind and compass, precipitation, temperature, humidity and pressure or solar radiation
- Noise Level
2. The Air Quality Station that learns
Co-location calibration against Reference Station
Step 1: Co-location phase: Air Quality Station will be deployed next to the reference station to collect data for 1 month. This is needed in order to calibrate Air Quality nodes against scientific reference stations.
Step 2-3: Data from the Reference station will be sent to Libelium Cloud through a CSV file. Meanwhile, all data gathered by Libelium Air Quality Station has been collected in the cloud.
Step 4: Then the calibration process starts in the Model Factory section from our Cloud. This is where Artificial Intelligence takes part, allowing the user to start predictive models.
Step 5: Once the AQS node has been calibrated and trained it is ready to be deployed.
*Remember that you can calibrate against the reference station more than one AQS node at the same time.
Calibration against Golden node
Step 1: Co-location phase: Your Air Quality Station previously calibrated against Reference Station is now named Golden Node.
A “golden node” is an Air Quality Station node previously calibrated by co-location process. This means that a first “Co-location” phase must be completed prior defining the device as “golden node”.
*This phase is interesting in case the project requires a large number of Air Quality Stations. In this way, it is possible to calibrate the remaining nodes with the node that was calibrated against the Reference Station in phase 1 (now called Golden Node).
3. Air Quality Station + Libelium Cloud
Data extracted from Scientific Reference Air Quality station is used in Artificial Intelligence (AI) model automation specifically for every project.
Libelium Cloud is the new software platform that allows the management of an IoT project from the beginning to the end.
4. Technical Features
- Libelium Cloud allows the user to execute remote Over The Air Programming (OTA), parameter configuration and reboot via LTE network
- 4G connectivity
- Easy to install, no batteries needed
- Simply connected to 220 V
- Libelium Cloud provides artificial intelligence and different graphs, dashboards and alerts to visualize data
Innovate new solutions
for the Internet of Things Market
Libelium participates in a project co-financed by the Spanish Ministry of Economy
Libelium participates in a project co-financed by the Spanish Ministry of the economy that promotes research to innovate new solutions for the Internet of Things Market.
The project “New device for high-precision monitoring and multivariate analysis of environmental factors’ has been co-financed by the Ministry of Economy and Business. This project is in the field of Digital Enabling Technologies (THD – 1/2019), within the State Plan for Scientific and Technical Research. File Number TSI-100110-2019-24
Interested to know more?