Product: Cyprus TreeMapper: Detection of all trees around Cyprus

Description: During the CO-FOR-IT project, we developed an online platform, empowered by artificial intelligence (AI), computer vision (CV), deep learning (DL) and geospatial analysis, allowing G/C and T/C stakeholders (i.e. NGOs, citizens, citizen initiatives) to optimize their decision-making in afforestation efforts. Collaboration between the two communities was encouraged, an element that is vital for exchanging best practices, supporting afforestation events through volunteers from both sides and raising environmental awareness, stressing the urgency of collaboration on this global matter that affects everyone on the island.

As part of this project, we developed a DL-based model, which used high spatial resolution satellite imagery to detect and count all trees around Cyprus. The final product was a GIS layer that detects and counts all trees around the island. A total of 54,731,274 trees have been identified, with more than 90% accuracy. In the 10% error, there are trees that are occluded or highly dense forested areas which make individual tree detection and counting difficult.

Techniques used: Satellite imagery, Deep learning, GIS and geospatial analysis

Output: To be provided as a service, as part of the Gaea environmental digital twin online tool.