Kohtari, a water technology company, has launched BloomIQ, a predictive monitoring platform designed to help water companies forecast algal bloom risk before blooms occur. The platform uses artificial intelligence, machine learning and multiple environmental data inputs to shift water utility operations from reactive monitoring to evidence-led prediction.
What Is BloomIQ and How Does Algal Bloom Prediction Work?
BloomIQ integrates environmental, weather and water quality data alongside historical records and optional drone observations. By processing these inputs through machine learning models, the platform identifies patterns associated with algal bloom conditions and generates early warning intelligence for water operators.
The system is designed to give water companies greater lead time before a bloom event develops — enabling earlier tactical and operational responses rather than reactive treatment following a bloom’s appearance.
Stuart Evans, Chief Technology Officer at Kohtari, said: “Using AI and multiple data sources to provide early visibility of bloom risk, BloomIQ enables water companies to make that important shift from merely reacting to algal blooms to actively predicting them. By enabling teams to act much sooner, they can build water quality resilience, improve public trust and reduce operational costs.”
Evans added: “It brings fragmented data signals together, applies machine learning, and turns bloom risk into something usable. Earlier intelligence changes decisions at every level: tactical interventions in the short term, better operational planning across the reservoir and treatment process, and stronger strategic and capital decisions over time.”
Algal Blooms: A Growing Risk for Water Utilities
Algal blooms — driven by rising temperatures, changing rainfall patterns and nutrient pollution — present a growing operational and compliance challenge for water companies globally. Blooms can affect drinking water sources, disrupt treatment processes and create reputational risks for utilities responsible for public water supply.
In England, 84% of surface waters are affected by nutrient pollution, according to the Environment Agency (2025). Excess nutrients, particularly phosphorus and nitrogen from agricultural runoff and wastewater, are a primary driver of algal bloom formation in reservoirs and freshwater bodies.
Reactive monitoring approaches — which detect blooms after they have formed — leave limited time for treatment intervention. Predictive platforms such as BloomIQ aim to address this gap by providing forward-looking risk assessment based on environmental conditions.
BloomIQ Algal Bloom Prediction: Key Platform Features
- AI and machine learning-based bloom risk forecasting
- Integration of weather, environmental and water quality data streams
- Historical data analysis to improve prediction accuracy
- Optional drone observation data input
- Designed to support tactical, operational and strategic decision-making for water utilities
Kohtari’s Recent Strategic Appointments
The BloomIQ launch follows Kohtari’s recent appointment of Lord St John of Bletso as Strategic Adviser. Lord St John of Bletso is a crossbench peer in the House of Lords with a background in technology and business advisory roles.
For more information about Kohtari and the BloomIQ platform, visit kohtari.ai.
For further coverage of water quality technology and digital water innovation, visit the H2O Global News Technology section.
FAQs
What is BloomIQ?
BloomIQ is a predictive water quality monitoring platform developed by Kohtari. It uses artificial intelligence, machine learning and environmental data inputs — including weather, water quality, historical records and optional drone observations — to forecast the risk of algal bloom events before they occur. It is designed for use by water companies managing reservoirs, freshwater bodies and drinking water sources.
Why are algal blooms a problem for water companies?
Algal blooms can contaminate drinking water sources, disrupt water treatment processes and create significant public health and reputational risks for water utilities. They are driven by a combination of rising water temperatures, changing precipitation patterns and elevated nutrient pollution — particularly phosphorus and nitrogen — in surface waters. The Environment Agency reports that 84% of English surface waters are currently affected by nutrient pollution.
How does predictive algal bloom monitoring differ from reactive monitoring?
Reactive monitoring detects a bloom after it has already formed, leaving water operators limited time to respond before public health or operational impacts occur. Predictive monitoring uses environmental data and machine learning to identify conditions likely to lead to a bloom event, giving operators earlier warning and more time to implement preventative or mitigating measures.
