What is the difference between Air Quality Modelled data and real-time data from devices on the ground?
This is a common question asked by our customers, so we thought it would be a great opportunity to share our thoughts after the launch of Google’s Air Quality API yesterday.
The new Google Air Quality API is a fantastic tool that will offer developers, like us, the opportunity to integrate air quality data for more than 100 countries across Europe, Asia, Africa, Australia and America. Building on Google Maps’ existing air quality layer, this new API pulls together data from government monitoring stations, satellites and meteorological data to provide a local universal index. Google’s purchase of Breezometer certainly helped them to escalate this development.
Combined with live traffic information this will enable customers to understand congestion data, and car volumes in an area and using machine learning, the app will predict levels of different pollutants at any given time.
The biggest advantage of modelled data is that it can provide a broad spatial coverage, offering insights into air quality levels across a wide area. Models using complex algorithms can also add a predictive capability based on various factors such as emissions, meteorological conditions and geographical features.
However what modelled data lacks is fine-scale resolution, which can lead to inaccuracies when assessing localised air quality. Modelled data might tell you that your air quality is good, taking data from government stations that are several miles apart. But what about the construction site next door that’s emitting dangerous levels of PM2.5 for a given period of time, or the roadside pollution increased dramatically by a car on fire? Modelled data does not capture all the dynamic factors that affect air quality, leading to discrepancies between predicted and actual values.
Devices on the ground such as Airscan, provide low-cost monitoring and provide real-time measurements of air quality, enabling timely responses to changes in conditions. Airscan offers detailed information about air quality at specific locations, which is essential for assessing impacts on local communities. These low-cost sensors are validated for accuracy against government static monitoring stations and can help validate modelled predictions, improving the accuracy of modelled data. Airscan is a direct measuring tool that provides more accurate data on actual exposure levels.
Combining modelled data and ground-based data from devices can provide a more complete picture of air quality. Integrating all these sources only enhances the accuracy and reliability of air quality assessments, supporting informed decision-making and environmental management.
We look forward to working with Google and other platforms to ground-level disseminate Airscan's ground level real-time data. By working together we can offer a much more accurate data set.