Surveillance is fundamental to control the spread of plant pests. Currently, it relies on trained personnel visually inspecting plants for symptoms. Aerial surveys using RPAS, equipped with advanced cameras, may facilitate surveillance by spotting early signs of pests without needing to inspect every plant, especially in hardly accessible areas.

This method is particularly useful when infestations are sparse within landscapes or affect young trees that are difficult to detect with satellites. RPAS can capture images in hyperspectral, multispectral and thermal domains, helping to detect stress in trees caused by pests even before symptoms are visible, and distinguish it from natural stress.

In FORSAID, we will focus on two key species:

Remote sensing technologies, like satellite, airplane and drone images, produce a large amount of data that can help monitor forest canopy health and detect pest damage across vast areas. However, analysing and interpreting such data volumes manually is slow and requires expert knowledge. In FORSAID, we use deep learning-powered computer vision to speed up and improve this process.

These deep learning models are trained with images where pest-affected trees have been identified through field surveys or insect traps. By learning spectral and textural patterns in these images, the models can automatically detect similar occurrences in images of other areas. This enables us to find areas at risk or already affected, even in large and remote forest areas, and monitor changes in forest health over time.

Our goal is to improve early detection of pests in key tree species like oaks, pines and spruces, helping forest managers take timely actions to reduce damage, boost forest resilience and maintain ecosystem services.

Leveraging remote sensing coupled with computer vision, we aim to automate the production of large-area, yet spatially detailed, cover maps to address three main questions:

Given the predominant academic background of the FORSAID consortium, it is crucial to ensure that the studies and innovations developed within the project will benefit a wide range of stakeholders and practitioners across the EU. A multi-actor approach is deployed as a backbone of the project to maximise impact and achieve transformative change towards a comprehensive forest pests monitoring system. In order to reach this overall goal, we initiated the creation of a Committee of Stakeholders, a panel of relevant practitioners with complementary activities and backgrounds (National Plant Protection Organisation, tree nurseries, forest owners, forest managers, customers, policy makers, urban tree managers) as well as an interest or expertise in forest pests. This committee will be involved at various stages of the project and contribute to the co-creation of the research actions. Different engagement methods will be implemented to benefit from the Committee of Stakeholders expertise:

Forests provide essential ecosystem services, making their protection against environmental threats crucial. A growing challenge in Europe is the rapid spread of forest pests, which causes major ecological and economic damage. As demand for effective solutions increases, digital technologies are emerging as powerful tools to address this issue.

The FORSAID project brings together 17 partners from 10 countries to create an innovative, cost-effective toolkit for monitoring forest pests. Focusing on nine high-risk species (three fungi, five insects, and one nematode), the project aims to enable timely intervention to prevent forest degradation.

Across its six Work Packages, FORSAID will improve existing digital solutions and develop new ones. Remote sensing via satellites and drones will help map areas of interest and identify pest disturbances. Automated insect traps will complement this effort on the ground by employing deep-learning algorithms capable of continuously analysing large amounts of incoming data. In addition, automatic species identification will simplify and quicken detection. Environmental DNA analysis will further support early pest detection.

To ensure long-term impact and sustainability, economic assessments and stakeholder consultations will be conducted. Citizen science input will also be integrated to make tools accessible and user-friendly for professionals and the public. This multi-actor, interdisciplinary approach aims to deliver practical, scalable solutions for forest monitoring across Europe.