A good quality small sensor air quality monitoring system should last 10 years or more, and of course certified monitoring stations (reference, FRM, FEM) should last much longer.

Looking at the many small sensor systems used for outdoor air pollution monitoring, the question may be ‘how long will my air quality monitor work between services’? The best systems operate for two years between sensor changes, and sensors should be low cost and locally replaceable, with no need to return equipment to the manufacturer for service or calibration.

Whether considering the operational life of the product or time between each service, it is important not to assume that all products are the same. Some systems are not designed to work for more than a year or so, which might meet the needs of a shorter project and budget, but it may cause a series of unscheduled equipment failures in the middle of an important monitoring period. So, it’s worth asking for examples of long-running projects where long-term operation of the system can be proven.

Any intervention during the operation of an air quality system costs money, even if it is ‘only’ the time and effort of local teams, so this must be minimised. Scheduled service work is undesirable, but unscheduled maintenance demands are worse. AQMesh sensor replacements are based on carefully calculated duty cycles – balancing initial costs against expected life and product performance – and the pods have been proven over years of operation around the world.

Of course, any equipment will be affected by operating conditions but small microsensor users should not expect their system to fail prematurely in harsh conditions. ‘Fit for purpose’ systems will be proven in intense heat, heavy rain, strong winds, freezing temperatures and snowfall: an expected 10-year lifetime should not just apply to easy conditions.

Having said all that, product lifetime will always be extended by careful use and following the manufacturer’s advice. The AQMesh user manual is now supplemented by a range of remote diagnostic tools, which detect signs of product ‘distress’, such as lower voltage from a dirty solar panel or potentially blocked air sample path.

Even if few air quality monitoring projects extend to 10 years, a product which is designed to last that long is fit to be used in a series of projects and can be upgraded or traded in, as requirements change.

Here at AQMesh we have a number of long-standing users who re-use their pods for new projects, and we are happy to discuss how we can help you with your own air quality monitoring requirements.

So how do you do it? Many presentations at the recent ASIC conference revolved around calibration of small sensor air quality systems, including that given by AQMesh Technical Business Development Manager, John Downie. Offered the opportunity to poll the ASIC audience, we chose to ask delegates ‘Please indicate which of these calibration methods for small sensors you would consider for your small sensor network’. Whilst numbers responding were not huge, ‘periodic co-location of each instrument with FRM/FEM creating seasonal correction factors’ came out top, indicating a thorough – if labour-intensive – approach is generally most common and taken as the ‘norm’.

So what if you don’t have the ‘boots on the ground’ to carry out the many instrument movements that would be necessary with a network of any size? Is there a short-cut? Can AI help? The poll did show that about a quarter of respondents were considering ‘desk-based calibration, using machine learning or AI’, about twice the proportion thinking about ‘desk-based calibration using network calibration method without machine learning or AI’.

We tried using AI on electrochemical sensor output a few years ago but found that – at the time – the machine learning was very good at latching onto interfering factors, such as temperature, and less good at finding the weak (valid) signal in amongst the noise. We were greatly impressed by the later (non-AI) network calibration work done by University of Cambridge, our partners in the Breathe London pilot, and have developed our own approach. This series of repeatable calculations can be applied to a network of five instruments upwards and we feel there are some clear differences (advantages, of course) comparing the AQMesh approach to local calibration with AI-driven approaches:

The fundamental issue with machine learning and AI being used either for compensation of sensor interferences or for calibration adjustments is that their whole premise is to “evolve”: they spot differences and change to account for those changes. This means that over time the results may be closer to reference, but they will never follow the same process for adjustment as they did previously. This raises significant traceability questions about when processing changes and makes it impossible for these methods to become certified to a standard which require a fixed processing of inputs, managed by a version number.

It’s worth noting that PAS 4023 (Annex D) distinguishes between sensor systems that are ‘self-contained’ – with readings derived by the system alone, using a series of repeatable calculations – and those that require training against a reference station. The PAS also emphasises how important it is that individual sensor systems should perform very similarly to one another, so that remote comparisons across a network can be made with confidence. Another reason why a proven, global correction algorithm used by every instrument has the edge over individual site-based AI. Strong inter-instrument comparability also means that a network can be meaningfully compared against itself, in the absence of a reference station, as offered by AQMesh’s network normalisation option.