GUARDEN’s main mission is to safeguard biodiversity and its contributions to people by bringing them at the forefront of policy and decision-making. This will be achieved through the development of user-oriented Decision Support Applications (DSAs), and leveraging on Multi-Stakeholder Partnerships (MSPs). They will take into account policy and management objectives and priorities across sectors and scales, build consensus to tackle data gaps, analytical uncertainties or conflicting objectives, and assess options to implement adaptive transformative change. To do so, GUARDEN will make use of a suite of methods and tools using Deep Learning, Earth Observation, and hybrid modelling to augment the amount of standardized and geo-localized biodiversity data, build-up a new generation of predictive models of biodiversity and ecosystem status indicators under multiple pressures (human and climate), and propose a set of complementary ecological indicators likely to be incorporated into local management and policy
Why is the project is necessary?
To monitor biodiversity in local habitats across Europe, and to monitor the progress of interventions to restore nature, it is important to have rapid nature surveying. Images and sounds analysed with AI can help, but these are not yet at the appropriate readiness level, nor integrated into ecological monitoring pipelines or policies.
What kind of innovations will the project bring to the field?
The project will introduce continental-scale image and sound recognition for nature, as a service. Naturalis is developing new machine learning algorithms for recognising the species of nature images and sounds, using modern algorithms and ensuring that they are tuned to be sensitive to the species and habitats that are important for European ecosystems.