Protecting and successfully managing our forests sustainably is a societal, governmental, economic and individual task and challenge. The effects of increasing natural disasters and climate change are clearly visible in our forests. Foresters and forest managers often face damaged forests—caused by calamities, windthrow or drought.
The characterization of forests has traditionally been time-consuming, costly and conducted in a 10-year cycle (forest management planning). The accelerated changes in forests require more frequent monitoring. Satellite and aerial imagery data allow for more up-to-date forest data with shorter and more flexible intervals. Digital automated analysis methods provide essential information for early detection, enabling measures to reduce forest damage and support a sustainable strategic forest conversion process.
Our ForestMonitor high-quality, annual information up to ad-hoc assessments. You benefit from tailored solutions and individual consultation.
Increasing open spaces caused by damage can lead to greater soil erosion. Prevent this by conducting:
With our remote sensing analyses, you can recognize and respond early to potential stress factors and natural hazards:
Forests are increasingly affected by climate-induced changes and abiotic and biotic calamities. Comprehensive knowledge of tree species composition and distribution is therefore of utmost importance for forest management and serves as a foundation for sustainable forest conversion. Currently, this information is available for only about 34% of Bavarian forests (state forests) from sample inventories.
The goal of the joint research project between IABG and LWF Bavaria is to develop an AI-based methodology for the automated classification of the most economically significant tree species in Bavaria (and Germany): spruce (Picea abies), pine (Pinus sylvestris), beech (Fagus sylvatica), and oak (Quercus spp.) using high-resolution remote sensing data.
The tree species classification is implemented using deep learning. A comprehensive training dataset was created by visual interpretation and manual digitization of individual trees and tree species groups to train the Convolutional Neural Networks (CNN) used for this purpose. The model is currently undergoing training and optimization.
The project is funded by the German Space Agency at the German Aerospace Center (DLR) with funds from the BMWi. For more details, refer to the publication in the journal Business Geomatics "AI for tree species recognition" (27.02.2024).
In recent years, the proportion of dying or dead trees has increased significantly. Beech dieback has been observed in northern Bavaria since early 2019. The volume of damaged wood caused by the infestation and population development of the bark beetle (Ips typographus) and copper engraver (Pityogenes chalcographus) also rose sharply: 1.9 million cubic meters in 2016, 3.55 million cubic meters in 2017, and 4.5 million cubic meters in 2018 (Triebenbacher et al., 2017, 2018 & 2019).
These phenomena prompted the Bavarian State Institute of Forestry (LWF) and IABG to initiate the research projects BeechSAT (detection of beech dryness) and IpsSAT (detection of different stages of bark beetle infestation). Various optical satellite and aerial images were compared using different machine learning (ML) and deep learning (DL) methods. The study was conducted in representative areas in Bavaria.
The aim was to evaluate the benefits of the methods for forest owners (economic, ecological, social) and forest protection (phytosanitary). A particular focus was placed on assessing the practical suitability of high-resolution optical satellite data for the automated detection of bark beetle damage and beech dryness, with recommendations derived for implementation in a practice-ready procedure.
The MAIL project aims to identify potential carbon sinks (e.g. fallow land, wasteland, treeless slopes) across Europe and assess their suitability for afforestation. A tool is being developed to identify and adapt potential afforestation areas for CO2 storage. The medium-term CO2 storage potential of biomass will be modeled as a site characteristic.
The integration of current Copernicus data allows monitoring of the development of potential carbon sinks. This aims to raise awareness of managing marginal land and provide access to thematic maps on-demand for policymakers, stakeholders and researchers across Europe.
IABG identifies potential carbon sinks for Germany and Europe and assesses their use in a sustainable climate program. All activities are funded by Horizon 2020/MSCA-RISE 2018.
MAIL (Identifying Marginal Lands in Europe and strengthening their contribution potentialities in a CO2 sequestration strategy, GA No. 823805, H2020-MSCA-RISE-2018) is a European cooperation project funded by the Research Executive Agency (REA) involving various European research institutions and companies.
Please fill in the form and we will get in touch with you as soon as possible.
