Rewarding Nature Hackathon

This section breaks down the life-cycle of the Rewarding Nature Hack following the steps described in the main guide.



There are current agricultural policies that want to move towards enhancing biodiversity in the farm, specifically through sustainable grassland management practices. Beyond the talk and established policy goals, the question still remains: how?

How to make the enforcement of these policies effective and affordable to monitor?  It is well know that man-powered auditing is expensive. 

Herb rich grassland is recognized as one of the KPI’s for the Biodiversity Monitor for Dairy Farming, as these grasslands can have a beneficial impact towards nature, climate and the environment. But how to technically find these lands and measure their impact?



This is the phase where possibilities for identifying herb-rich grassland are explored. With the help of satellite data and AI these grassland types could be recognized from space. By spotting these lands, the farmer can be rewarded for his sustainable management efforts efforts.

This calls for impact based monitoring and compensation!



Here the most relevant stakeholders that partake in the biodiversity monitoring challenge are mapped out:

  • Sponsors: WWF-NL

  • Challenger: WWF-NL, BoerEnNatuur and RVO

  • Data Donors: RVO, NEO, AgroData Cube

  • Hackers:  experts in AI and machine learning, remote sensing, radar, and governance;  creatives and tech savvy coders and developers.



Existing studies by Ruth Howison in University Groningen suggest that radar might give us clues towards the identification of herbal rich grasslands from space. Getting her on board, as well as the stakeholders involved in the Biodiversity Monitor for Dairy Farming initiative were the main activities of the mobilization stage.



Teams 1 and 2: made use of satellite (radar | optical) data and created a method for processing and analysis meant to identify herb-rich grassland.

Team 3: created an app for farmers to upload geo-referenced photos thereby providing proof of the grasslands; computer vision is used for automatic classification of the photos.

Team 4:   developed a performance benchmark to provide farmers with an overview and insight into their biodiversity performance.



Follow-up assignments and even an events have been executed with farmers, government, research institutions, businesses and startups that are involved in the herbal rich grassland subject matter.