Page 25 - Landscapeeissue132(2)

TECHNOLOGY IN THE GREEN INDUSTRY

USING AI TO

IMPROVE Pollen counts
are often
difficult to
POLLEN predict during
spring when
counts are
highest
FORECASTS

Artificial Intelligence (AI) is being used sticky tape. The only challenge is that we need to have a period of
validation, so for a time, we will put a conventional volumetric trap
by South African scientists to detect next to the automatic AI counter to verify the accuracy of the analysis.
and classify pollen spores in real time, Once the AI has been sufficiently trained to recognise grains that are
indigenous to South Africa, it will be able to classify species very
which may improve forecasting of quickly. Main allergens such as grass, plane and cypress trees, as well
as fungal species such as Alternaria, Aspergillus and Cladosporium,
bio-aerosols that trigger respiratory should be easy for the AI to identify as these are found worldwide.
Pollen counts are often difficult to predict during spring when
illnesses like hay fever and asthma. counts are highest and the weather is changing daily. Having access
to reliable, real-time pollen readings will significantly improve
forecasting and help hay fever sufferers to mitigate bothersome
symptoms that include a runny or itchy nose, sneezing, itchy and
watery eyes, as well as nasal congestion.”

2023 pollen forecast with El Niño thrown into the mix
He says this year’s pollen season depends largely on the weather,
but that hay fever sufferers can expect higher than normal grass
counts. “We are already seeing high tree counts in Cape Town with
exceptionally high tree counts in Bloemfontein.”
The El Niño weather phenomenon could also influence the timing
Automated pollen sense counters are being set up in key biomes across the and severity of this year’s allergy season. It is typically associated with
country to provide real-time pollen readings. hot and dry conditions, but certain regions could receive increased
precipitation, along with higher than average temperatures leading
rof. Jonny Peter, head of the Division of Allergology and Clinical to enhanced pollen production.
Immunology at Groote Schuur and the UCT Lung Institute, who “The underlying influence of climate change makes the country
Palso leads the South African Pollen Network (SAPNET), says extremely vulnerable to the effects of El Niño,” remarks Prof Peter.
the monitoring of airborne pollen provides an important source “In Europe, El Niño has caused extreme weather events, and some
of information for the globally increasing number of hay fever and countries have reported earlier starts and extended pollen seasons.
asthma sufferers. In the UK, record grass counts were recorded.”
Up to now, scientists have manually counted airborne pollen
and spore types using volumetric air samplers that suck air from the SAPNET partners with SA Weather Service to help
environment, collecting the particles it traps on adhesive tape, which allergy sufferers
are then analysed under a microscope by a pollen expert. However, Prof. Peter says that in addition to the South African Pollen Network
the process is cumbersome and costly. With the latest developments providing allergy sufferers with up-to-date pollen counts, its recent
in image recognition methods and machine learning, automating partnership with the SA Weather Service (SAWS) will also give the
this process has become feasible. public and healthcare practitioners access to information related to
Prof. Peter says by combining cutting-edge technologies like AI air pollution, which includes carbon monoxide, sulfur dioxide and
and imaging flow cytometry, which measures the size, count, shape ozone – all of which are linked to the worsening of allergic diseases.
and structure of a cell, they can build a system for South Africa that “As the SAPNET expands, the aim is to provide information in real
can identify and categorise pollen more accurately and at much time of what is in the air – spanning the spectrum of air pollution,
faster rates. AI can also help to model historic environmental change. pollens, microplastics and other irritants. We’ll also be working with
Pollen grains from different plant species are unique and different communities to further research that is being done on
identifiable based on their individual features. Analysing which indoor pollutants which also play a big role, particularly in asthma
pollen grains are captured in samples from sediment cores in lakes and asthma exacerbation in children.”
can help scientists get a better grasp on which plants were thriving Thanks to funding from Clicks, Thermo Fisher, Glenmark
at any given point in history, potentially dating back thousands to Pharmaceuticals, Cipla and Dr Reddy’s, SAPNET currently covers
millions of years. Its numerous applications are transforming the way ten biomes which include Cape Town, George, Gqeberha, Durban,
scientists conduct research and accelerate scientific productivity. Johannesburg, Pretoria, Potchefstroom, Bloemfontein and Kimberley.
Two AI counters have already been set up in Pretoria and For up-to-date pollen counts per region, visit pollencount.co.za.
Kimberley, with two more in Cape Town and Durban coming on line Knowing the daily pollen count will assist hay fever sufferers to better
soon. Bloemfontein and Johannesburg will also follow. manage their condition as grasses, weeds, trees and shrubs pollinate
Prof. Peter says: “It works in a similar way to the volumetric spore at different times.
trap that sucks pollen onto the cellulose membrane, but then it
takes a photo of it. From there, AI takes over and it is trained using Information and photos supplied by Meropa Communications on behalf of
large volumes of images to recognise the individual grains on the the UCT Lung Institute. n

Check us out www.salandscape.co.za Landscape SA • Issue 132 2023 23