ReTreevAIble

While local governments are trying to mitigate the risks associated with increased urbanisation such as flooding danger and decreased air quality by focusing on urban forestation, they lack know-how and specific data to come up with detailed and effective plans to reduce and/or reverse the phenomena of green areas being replaced by grey areas. To add to the potential hazards of increased urbanisation and decreased urban green, urban forestation is a complex topic which requires expertise and detailed specific plans to reach the desired KPI's set by the local city government. Regional differences and inter-specie tree differences make for a complex scenario in which no generic solution design can be designed fit for all purposes. Within this project we propose to offer a solution by developing ReTreevAIble, providing individual tree data and analytics in an intuitive solution by which policy makers and other stakeholders are able to make decisions in a data-driven way rather than extensive fieldwork and data collection. We aim to develop ReTreevAIble which is built on state of the art technologies and functionalities, aimed to support decision making, urban tree planning and providing high quality data of tree species, features and scenario analytics on tree health, biodiversity and the environment to third parties. This will be done using state of the art AI and ML technologies in conjunction with human centred design approaches. By cooperating with three leading AI companies active in complementary domains, we will be able to deliver a comprehensive solution which incorporates new methodologies throughout the entire AI process, from data collection, remote sensing and processing all the way to an intuitive eXplainable AI (XAI) design. Although the target innovation will be tested and validated with urban trees and parks during the subsidy period, it will be extended for tree populations within rural and forests.