Mapping “Dark Corridors” for Bats in Brussels
Challenge Background
Animals in general are facing an unprecedented wave of extinction. Bats are especially impacted by the changes brought by humans. The causes for this collapse are multiple, but one of them is the light pollution.
Lights are modifying bats environments. Insects are attracted to light, which gives some bats an interesting point to feed, but it also present numerous challenges for them :
- Predators relying on light and day predators are able to catch them - Light disturbs their habits, leading them to miss their optimal feeding time
Some species might avoid light altogether, leading to a fragmented habitat, disturbed feeding routes and more vulnerables populations
In recent years, more and more initiatives have been launched to reduce light pollution in Brussels, to preserve bats (and other animals) communities.
The Problem
The goal of this project is to create a map of lightning pollution in Brussels, to find the areas where light pollution has been effectively tackled and areas where improvement are dues.
An addition would be to add on the map the feeding point of bats, and to look for “dark corridors”, i.e. non-lightened area giving the possibility for bats to move from one point to another.
The project results will be made open source. Data should be available to NGOs working in species conservation, public institutions looking to improve their neighbourhood and concerned citiern looking for more information.
Goal of the Project
- Build a map of the light pollution and “Dark corridors in Brussels, that could be applied to other cities.
- GitHub Repo with open source code
- Curated dataset hosted in AWS or Google for open access
Project Timeline
Data collection:
- Nighttime image of Brussels
- Observation points of bats and/or map where water is available
Data cleaning and preparation
Find dark corridors present in Brussels
Test model
Optional : Find feeding patterns of bats based on observation and water
Build a model of potential now ecological corridors
Write a report and test the models
What you'll learn
- Collect satellite images and extract relevant features.
- Collect tabular data with geographical data and map them on satellite images.
- Build a machine-learning project with geographical and satellite data.
First Omdena Local Chapter Project?
Beginner-friendly, but also welcomes experts
Education-focused
Duration: 4 to 8 weeks
Open-source
Your Benefits
Address a significant real-world problem with your skills
Build your project portfolio
Access paid projects (as an Omdena Top Talent)
Get hired at top organizations
Requirements
Good English
Suitable for AI/ Data Science beginners but also more senior collaborators
Learning mindset
Application Form
This Challenge is hosted by:
Become an Omdena Collaborator

