AI system
- System
-
SES Water smart network: 1,000 flow and pressure sensors with AI-based predicted-level leak alarms (vendor not named)
- Model
-
Not assessed
- Release
-
Exact release not established.
- Provider
-
Not assessed
- Role
-
The software compared sensor readings with predicted values to flag possible leaks.
- Configuration
-
The deployment used Aquasuite Burst.
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Dense sensor coverage (1,000 flow and pressure sensors) across a compact supply area. Predicted-versus-actual comparison raising alarms within minutes. Repair crews dispatched on alarms rather than customer reports.
- Human oversight
-
Not assessed
- Relation to AI
-
The BBC report, an independent source with named utility staff, describes the AI only in general terms (prediction of expected levels, alarms within minutes). The developer is unnamed. The 40% figure is the deployer's claim, so the AI's share of any leakage reduction is unverified.
- AI contribution
-
Not assessed
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
reduced leakage run rate times by up to 40%
- Category
-
Reduced Carbon Emissions
- Status
-
Not assessed
- Beneficiary groups
-
Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
reduced leakage run rate times by up to 40%
- Comparison
-
leak run times before the sensor network
- Results
-
Reference: previous leakage run rate times (not quantified). Result: reduce our leakage run rate times by up to 40%.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Operator: Sutton and East Surrey (SES) Water.
- Jurisdictions
-
Benefit: Surrey,
United Kingdom. Operator: United Kingdom. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Sensor density and telemetry sufficient to localize anomalies. Crew capacity to act on alarms quickly. Independent reporting of leakage volumes to confirm the claimed effect.
- Replication attempts
-
Not assessed
- Later findings
-
No dated development after March 2024 was found; the vendor's undated case study repeats the 40% figure.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0169-source-0001–0003
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Independent, Developer
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
Organizations: The up-to-40% reduction in leakage run rate times is the utility's own claim without an independent figure. Society: Leakage reduction targets (15% over five years) are stated as plans; no measured outcome is attributed to the AI.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Water infrastructure. Water distribution leakage management.
- Purpose
-
The smart network was built to detect leaks early from sensor data against predicted levels and dispatch repairs. The reduced run times are its intended use.
- Dates
-
Date basis unassessed: 2024 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: dbaab786bf86…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
Case report Developer
Royal HaskoningDHV (undated). SES Water achieves a 40% reduction in leak run time with Aquasuite. Haskoning project page.
-
News report Independent author
Yvette Austin, 'SES Water: Artificial intelligence helps reduce water leaks', BBC News, 11 March 2024
Sutton and East Surrey (SES) Water has installed 1000 sensors underground that monitor flow and pressure, then send data back to base.
Our smart network has enabled us to reduce our leakage run rate times by up to 40%.