AquaTwinAboutSyncing
InitializingSimulated plant
–°C
Temperature
–g/L
Salinity
–NTU
Turbidity
–
pH
--:--:--
SIM --:--:--
Khalifa University–UNESCO Global Water Hackathon 2026 · Theme 3

AquaTwin

A physics-informed, self-calibrating digital twin for resilient and safe seawater desalination.

Physics + ML residualCalibrated uncertaintyAquaGuard safety layerWithholds outside its envelopeRuns in the browser

Aligned with the UN Water pillars

The hackathon's six themes · SDG 6 · simulated results

  • 01

    Water security & sustainable desalination

    Keeps SWRO output on specification and on demand through Gulf stresses. Under a +15 % salinity shock, fixed setpoints violate a limit for 21.3 h of 24; AquaTwin for none.

    Scenario Lab
  • 02

    Water reuse, circularity & resource efficiency

    Treats membranes as assets: cleaning is planned from a fouling forecast about half a day ahead instead of being triggered by a threshold, and fouling rate is an optimisation objective.

    Membrane Health
  • 03Our theme

    Smart, digital & AI-enabled water systems

    Physics-informed machine learning with calibrated uncertainty: permeate-flow error 4.9 m³/h per train, against 48.0 for the calibrated physics and 9.7 for machine learning alone.

    Model Intelligence
  • 04

    Water quality, health & environmental protection

    Permeate quality is a hard limit, checked at the edge of the model's uncertainty; quality excursions are forecast two hours ahead and rehearsed before they happen.

    Water Quality
  • 05

    Energy–water nexus & climate resilience

    Energy and carbon are first-class objectives. Grid power caps are honoured by pre-filling storage, and the energy cost of resilience is reported, not hidden: 0 to +2.8 % specific energy.

    Energy & Carbon
  • 06

    Integrated systems, governance & cooperation

    Built to be audited: every number is labelled by provenance, every recommendation states the limits it was checked against, and outside its validated envelope the twin withholds advice.

    Validation

About this prototype

AquaTwin is a digital twin for seawater reverse-osmosis (SWRO) desalination. It combines a reduced-order physical model of the plant with a machine-learning residual that corrects what the physics misses, calibrates itself continuously against telemetry, forecasts membrane degradation, and recommends operating strategies that a deterministic safety layer, AquaGuard, must approve before they are shown to an operator.

Built by Team Kanban for the Khalifa University–UNESCO Global Water Hackathon 2026, theme Smart, Digital, and AI-Enabled Water Systems.

This is a research prototype. The plant it monitors is simulated: a higher-fidelity reference plant model stands in for a real SWRO facility so that ground truth is known and every claim can be tested. It is not connected to any real plant and is not intended for operational use.

Where the numbers come from

Simulated
Plant behaviour produced by the reference plant simulator, the stand-in for a real plant in this prototype. All live telemetry is simulated.
Modeled
Outputs of AquaTwin's hybrid model (physics + ML residual), e.g. predictions, expectations and forecasts.
Estimated
Derived quantities with material outside uncertainty, e.g. carbon from an average grid intensity.
Assumed
Design choices and parameters without a specific source (flagged in the code and model documentation).
External ref.
Values taken from published sources: membrane datasheets, seawater property correlations, WHO guidance, grid data.
Measured
Not used. AquaTwin has not been connected to a real plant; no value in this prototype is a plant measurement.

Disclaimers

No organisation named in this prototype or its documentation (including utilities, plant operators, equipment manufacturers, universities or UN agencies) has reviewed, endorsed or partnered with AquaTwin. Names appear only to cite published sources or to describe the hackathon.

Performance figures are simulation results or model estimates and are labelled as such. They have not been validated on an industrial plant. AquaTwin does not use a language model for any prediction, control or safety decision.

The one-minute film

AquaTwin in under a minute: a narrated motion-graphics pitch built from this application and its own simulation results. Every result shown is simulated. By Team Kanban. Voice: Kokoro-82M. Music: original, generated for the film. Sound effects: Kenney (CC0).

Methods and data sources

The full reference list, with notes on what was and was not verified, is in docs/REFERENCES.md.

Open-source software

  • Next.jsMIT
  • ReactMIT
  • three.jsMIT
  • Tailwind CSSMIT
  • ZustandMIT
  • d3-scale · d3-shape · d3-arrayISC
  • MotionMIT
  • Geist and Geist MonoSIL OFL 1.1
  • scikit-learnBSD-3-Clause
  • NumPy · pandasBSD-3-Clause
  • TypeScript · tsxApache-2.0 · MIT
  • Playwright (QA)Apache-2.0

Credits

Concept, engineering, modelling and design: Team Kanban.

Prototype version 0.1 · synthetic data seed 20261101 · all experiments reproducible from the scripts in the repository.

AquaTwin
Digital twin offline