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.
Digital inspection B-waterways
Using machine learning models in combination with aerial or satellite photos and maps, B waterways are assessed to determine whether they have been cleared of vegetation.
Last change on 30th of July 2024, at 5:38 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
General information
Theme
Space and Infrastructure
Begin date
11-2020
Contact information
info@wdodelta.nl
Link to publication website
https://www.imagem.nl/schouw-mapp/ https://www.wdodelta.nl/satelliet-controleert-of-sloten-goed-zijn-schoongemaakt
Responsible use
Goal and impact
Goal:
The aim of the digital inspection is to carry out the inspection on B waterways (inspection ditches) more efficiently (in terms of time and costs).
Impact:
The consequences of digital inspection for a plot owner (company or citizen) are minimal.
- The digital inspection reduces the supervisory burden for all plot owners.
- With the help of the Schouw M.app (dashboard and field application), the water board can provide better service to plot owners in the event of a 'dirty' ditch.
- Instead of water board employees physically checking all inspection ditches, which could also reveal other things and could mean a greater invasion of privacy, only the 'dirty' ditches are now checked.
- So through this method, attention is drawn to the situations that are not good. As a result, the plot owners are rewarded with a lower supervisory burden if they have fulfilled their obligation.
Considerations
Advantages:
- Less supervisory burden
- Less staff deployment
- Inspection execution within 1 team
- Uniform working method
- More service to landowners
- Digital inspection has technical limitations
- Not all ditches can be assessed digitally (e.g. ditch located under trees)
- Satellite photo; no influence on the moment of recording (when it is taken and the result is weather dependent)
Human intervention
- Prior to the digital inspection, training data (photos of ditches that are clean) is provided by the water board. This is for the purpose of training the algorithm/machine learning.
- Human, visual control or basis of the result of the digital inspection, via a computer dashboard. (screen inspection)
- After the digital inspection and screen inspection, a physical inspection of 'dirty' ditches is carried out by water board employees.
Risk management
A risk is false positive results; where the ditch is not clean, but is assessed as clean.
The ditch may not have been maintained, while it should have been. And the responsible landowner is not informed (warned) by letter.
If the result of the digital inspection of an inspection ditch is questionable, it is classified as 'not clean'. These ditches are checked again by an employee during the screen inspection. This reduces the chance that a dirty ditch is still classified as clean.
Legal basis
The inspection of waterways is laid down in the Water Act and the By-laws (regulations) of the water board
Links to legal bases
Waterwet: https://zoek.officielebekendmakingen.nl/wsb-2017-6667.html
Operations
Data
aerial photographs and satellite images, cadastral data, map of waterways
Links to data sources
- Kaart watergangen: https://wdodelta.maps.arcgis.com/apps/PublicInformation/index.html?appid=f4d70462441647d1ab9073fd9f333d1c
- Kadastrale data: https://app.pdok.nl/viewer/
Technical design
Step 1:
The algorithm (machine learning) searches for a relationship according to a specific statistical method between the bands in a multi-spectral satellite image (or aerial photograph) and locations in waterways that are assessed as clean or not clean by a water board employee.
Step 2:
The relation is stored in a so-called machine intellect that is used in the classification of waterways for the entire area to be inspected, whereby the result is presented as clean or not clean locations in the waterways. In case of insufficiently clean locations in a waterway, the waterway is classified as not clean.
External provider
Image
Similar algorithm descriptions
- The algorithm sees from aerial photos in which watercourses there have been attenuations.Last change on 12th of March 2025, at 8:13 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- 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
- To correctly determine the level of urban water and sewerage, we prevent negative side effects caused by a relatively high or low level of urban water. In doing so, we contribute to the safety of residents and a cleaner city.Last change on 5th of September 2025, at 13:01 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Uthiek, DPIA
- Status
- In use
- Real-time algorithm that continuously determines the amount of water (the water flow rate) routed to each of the 7 streets of sewage treatment plant RWZI Amsterdam-West.Last change on 6th of March 2025, at 10:53 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- This algorithm falls under Digital Moat. The boating traffic model has been under development since 2022 and will reflect capacity by canal.Last change on 10th of September 2025, at 9:24 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use