Algae blooms can have severe adverse effects on the environment, posing a threat to drinking water quality, birdlife, and aquatic life. To tackle the issue, Welsh Water is trialing a new project that uses artificial intelligence (AI) to improve the way it monitors algae levels in its reservoirs.
Contaminated drinking water
Algae and cyanobacteria are responsible for the production of taste and odour compounds and toxins such as microcystin, which can contaminate drinking water. As the climate changes, algal blooms are predicted to be more frequent and intense, posing a significant risk to public water safety.
Traditional algal monitoring is often slow and resource-intensive, making it hard to predict and preempt algal risks. However, AI-enabled technology can transform algal monitoring into a high-throughput, high-accuracy lab-based or field-based process that will provide a detailed analysis of algal blooms.
Welsh Water has received £385,000 in funding from Ofwat’s Innovation Fund, which it hopes will transform its algal monitoring systems with AI. This is part of a wider £40 million Water Breakthrough Challenge.
How does AI algae monitoring work?
By combining AI with a smart sensor network and analysing data, algorithms can identify high-risk areas for algal blooms. Information can then be used to build models that predict future algal bloom events. Providing water companies with this valuable data then enables them to act early, more efficiently and in a more targeted manner in case an outbreak of algal blooms occurs thus reducing costs.
The technology implementation is less intrusive and data uploads and analyses are done remotely, saving resources and time significantly. The use of AI also makes it easier to compare real-time water quality data with historical data sets, increasing understanding of algal blooms while allowing for more sophisticated prediction models.
“Ensuring drinking water is safe to drink requires constant monitoring and prediction of risk. This is true for the water quality risks associated with algae and cyanobacteria e.g., taste and odour causing compounds which are predicted to increase with frequency and intensity with climate change,” said Phil Jones, technical development manager at Dŵr Cymru Welsh Water.
The technology implementation is less intrusive and data uploads and analyses are done remotely, saving resources and time significantly. The use of AI also makes it easier to compare real-time water quality data with historical data sets, increasing understanding of algal blooms while allowing for more sophisticated prediction models.
“Ensuring drinking water is safe to drink requires constant monitoring and prediction of risk. This is true for the water quality risks associated with algae and cyanobacteria e.g., taste and odour causing compounds which are predicted to increase with frequency and intensity with climate change,” said Phil Jones, technical development manager at Dŵr Cymru Welsh Water.
Taking algae monitoring one step further
Jones said that AI could potentially take algae monitoring further, with smart sensors and data analysis tracking algal blooms' movement in real-time. This would allow a better visualisation of the pollutants, thus giving companies more timely and accurate warnings.
Also, AI could monitor the environmental data of the bodies of water in which water is sourced and determine how they affect the ecology stability of the waters.
The technical development manager added: “Traditional algal monitoring is time consuming, resource intensive and does not provide sufficient data for predictive modelling of algal risks. This funding will enable a significant leap forward in algal analysis and accelerate the use of algal data to predict water quality risks. This will provide benefits to customers and wider society, as it will better equip the water industry to tackle current and future algal related water quality challenges.”
Also, AI could monitor the environmental data of the bodies of water in which water is sourced and determine how they affect the ecology stability of the waters.
The technical development manager added: “Traditional algal monitoring is time consuming, resource intensive and does not provide sufficient data for predictive modelling of algal risks. This funding will enable a significant leap forward in algal analysis and accelerate the use of algal data to predict water quality risks. This will provide benefits to customers and wider society, as it will better equip the water industry to tackle current and future algal related water quality challenges.”
