WC138 SeptOct 2024 - Flipbook - Page 36
TECHNOLOGY
Doorn reviews the use of AI to empower “theory-guided data
science,” which avoids some of the pitfalls of strictly data-driven
models. Doorn’s research suggests that the development and application of responsible AI techniques for the water sector should
not be left to data scientists alone. He argues that it requires
a concerted effort by water professionals and data scientists
working together, complemented with expertise from the social
sciences and humanities.
Unaccounted-for-water (UFW) is a key benchmarking parameter indicative of the operational and financial performance of a
water utility. Maximizing the use of information and communications technology (ICT) for UFW improves the quality-of-service delivery to customers.
Despite an increased application of numerical tools by water
utilities (Hydraulic Modelling 1.0), the digital transformation of
the water sector is lagging other sectors, such as energy. Cost-effective sensors combined with Internet of Things (IoT) brings a
paradigm shift for smart water management (Hydraulic Modeling 2.0), supported by AI and big data analytics.
Key areas for policy action include enabling ethics in smart
water utilities through regulation and public participation to
secure buy-in from consumers and to protect their personal data;
issuing guidelines for a smart water road map to move water
utilities toward a digital transformation; piloting Hydraulic
Modeling 2.0, first targeting the prognosis for UFW.
Here are just a few of the ways and areas whereby AI is being
applied in water-related engineering projects:
Water Quality Monitoring: AI algorithms can analyze data from
sensors to detect changes in water quality, identify pollutants,
and predict potential contamination events. This helps in early
detection and timely response to water quality issues. AI is used
to monitor and analyze water cycle data, including water quality,
usage tracking, and infrastructure problems.
Predictive Maintenance: AI-driven predictive maintenance
systems analyze data from sensors installed in water infrastructure such as pumps, valves, and pipelines to predict equipment
failures before they occur. This reduces downtime and maintenance costs. Oerther is convinced AI will help with identifying
and replacing existing lead service lines: “Incorporating historical
records with up-to-date measures of water quality is an example
of the use of AI to generate predictions. With nearly 9.2 million
lead services lines estimated to be in use in the United States,
the goal of replacing all of these by 2033 is a major undertaking intended to protect human health by reducing exposure to
neurotoxic lead.”
Smart Water Distribution: AI is used to optimize water distribution networks by predicting demand, detecting leaks, and
identifying areas with inefficient water usage. This helps in
reducing water loss, improving distribution efficiency, and ensur-
36
WATER C AN ADA • SEP TEMBER/OCTOBER 2024
ing reliable water supply. AI helps in identifying leaks, detecting
pressure-related issues, and optimizing water flow to improve
overall water supply efficiency.
Flood Prediction and Management: AI models analyze data from
various sources including weather forecasts, river levels, and
historical flood data to predict and manage floods more accurately. This enables authorities to take proactive measures to mitigate
flood risks and minimize damage. AI can predict and learn from
emergency events like water mainbreaks, enabling proactive
measures to be taken.
Water Resource Management: AI algorithms are employed to
optimize water resource management by analyzing complex data
sets related to precipitation, groundwater levels, reservoir storage,
and water demand. This helps in making informed decisions
about water allocation and usage. AI can optimize energy consumption in water treatment and distribution, reducing costs
and carbon emissions. AI provides sophisticated decision-making
support for operators by analyzing complex variables and offering
intelligent recommendations.
Water Treatment Optimization: AI is used to optimize water
treatment processes by analyzing water quality data in real-time
and adjusting treatment parameters accordingly. This ensures that
water treatment plants operate efficiently and meet regulatory
standards.
Environmental Monitoring: AI-powered monitoring systems analyze satellite imagery and other data sources to monitor changes
in water bodies, such as pollution levels, algae blooms, and habitat degradation. This information is valuable for environmental
assessment and management.
Desalination Optimization: AI algorithms are applied to optimize
desalination processes by controlling factors such as flow rates,
pressure, and membrane performance. This improves the efficiency of desalination plants and reduces energy consumption.
Water Conservation: AI-based systems analyze water usage
patterns and identify opportunities for conservation, such as
optimizing irrigation schedules, detecting leaks in residential
and commercial buildings, and promoting water-saving practices. Some global estimates suggest that leaking drinking water
intended for domestic off stream uses is on the order of nearly 30
per cent, with the U.S. suffering 17 per cent losses. Oerther looks
at the loss of distributed water as well as inflow and infiltration to
sewage and stormwater systems. Leakage detection is an example
of the use of AI for the analysis of anomalies. Given the amount
of energy used to provide water to homes and industries, a
savings of any small percentage of the total volume would reduce
greenhouse gas emissions.
These applications demonstrate that AI is already at work in
diverse dimensions of water management, quality, and distribution. As the technology advances, AI will play an increasingly
important role in the overall picture.
WAT E R C A N A D A . N E T
