Kontext

Forests play a vital role in the achievement of the objectives of the European Green Deal, by mitigating the negative effects of climate change and environmental degradation and at the same time by contributing to the transformation of the EU into a modern, resource-efficient and competitive economy, while ensuring no net emissions of greenhouse gases by 2050 and economic growth decoupled from resource use. However, forest trees are increasingly threatened by invasive pests. Trees in forests are long-lived organisms, which means they experience a higher exposure to multiple hazards during their lifetime and are likely to accumulate damage from several regulated pests and other stressors. Trees may have a higher probability to survive sporadic events (e.g., defoliation) than crop plants, but at the same time may be asymptomatic for a long time before displaying decline. These pathways contribute to the introduction of new organisms affecting tree health into a new region or continent. The potential of digital technologies to improve early detection, territory surveillance and phytosanitary measures needed to prevent and contain the damage caused by pests is enormous, but it requires a thorough matching of scientific knowledge and innovation as well as tools needed by stakeholders.

Objectives

The FORSAID project aims to develop a comprehensive suite of innovative digital technologies for the early detection and monitoring of regulated forest pests. By integrating the Internet of Things, Artificial Intelligence and remote sensing, the project seeks to enhance pest surveillance and mitigate the spread and impact of quarantine forest species. A multi-actor and multidisciplinary approach ensures that these technologies are practical, scalable and tailored for effective adoption across EU forests.

Activities

FORSAID employs a combination of innovative digital tools to improve forest pest detection. Remote sensing across multiple spatial scales will allow the early detection of damage symptoms. Automated traps, enhanced by deep learning, will remotely analyse images to identify target species. Additionally, innovative eDNA barcoding protocols will be implemented for species detection. Citizen science data will also be explored as a key resource for species detection. An economic analysis will assess the costs and benefits of digital surveillance, while stakeholder collaboration will help develop practical implementation guidelines.