Direct naar content

You are here:

  1. Home
  2. Algorithms

Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.

Discharge forecast model Roer

Limburg water board

The algorithm provides a forecast of the discharge of the Rur river at Stah, Germany. Input data is measured discharge from various monitoring points, fallen precipitation, expected precipitation and evaporation. Outputs are hourly forecasts up to 24 hours in the future.

Last change on 30th of April 2025, at 13:30 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

Organisation and business operations

Begin date

2020-01

Contact information

info@waterschaplimburg.nl

Link to publication website

www.waterschaplimburg.nl

Responsible use

Goal and impact

The purpose of the algorithm is to provide the most accurate forecast of the discharge of the Roer at Stah, so that WL can take timely measures to prevent flooding as much as possible.

Considerations

With conventional hydrological tools, it was difficult to arrive at a sufficiently accurate forecast because there are spillways between Jülich and Stah. These affect the surge through the Ruhr, but the way in which is difficult to model. By using machine learning, we have overcome this problem.

Human intervention

It is a decision support model. The content expert is responsible for interpreting the output and setting out actions if necessary.

Risk management

Software-wise via management and maintenance to keep code up to date, and where necessary re-train the model when sufficient, new data is available.

Operations

Data

Runoff measurements, precipitation measurements, precipitation projections, evaporation measurements

Links to data sources

  • Neerslag: https://www.hetwaterschapshuis.nl/neerslag-weer-informatie-waterbeheer
  • Verdamping: https://www.knmi.nl/kennis-en-datacentrum/uitleg/automatische-weerstations
  • Afvoer: https://www.waterstandlimburg.nl/Home/Waterstanden

Technical design

It is a linear regression of some 500 (non-linear) features.

External provider

RDHV

Similar algorithm descriptions

  • Data-driven Expectations drainage streams

    Limburg water board

    The model gives as output predictions of the discharge (in m3/s, average per hour) of streams at 13 measurement points. This is done based on 3 different weather models, so there are 3 different predictions per measurement point.

    Last change on 4th of August 2025, at 6:43 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Data-driven sewer management at Euvelgunne business park

    Municipality of Groningen

    Based on measurements, sewage discharge is controlled. The algorithm determines whether a valve for the transit is open or closed. This makes it possible to control where this water goes during periods of high rainfall.

    Last change on 5th of January 2024, at 14:22 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Forecast crowds and ballot paper usage at polling stations

    Municipality of The Hague

    Based on the turnout in the first 3 hours (according to the Polling StationApp), a forecast is made over the next 10 hours for crowding and ballot paper take-up.

    Last change on 23rd of August 2024, at 13:50 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Dashboard monitor

    Municipality of Steenwijkerland

    We use software to forecast the number of visitors in Giethoorn. These forecasts serve as a support tool for planning and deploying staff.

    Last change on 21st of May 2025, at 14:48 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Understanding future peak times at Civil Affairs counters

    Municipality of Groningen

    This algorithm, the forecasting model, provides insight into future peak moments at the municipality's Citizen Affairs desks. This allows additional staff to be hired in time for expected peak moments. This model also supports financial planning.

    Last change on 27th of June 2024, at 13:10 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use