Johannes Schumacher
Research Scientist
Authors
Giovanni D’Amico Davide Botticelli Giacomo Marcelli Walter Mattioli Gherardo Chirici Elia Vangi Costanza Borghi Piermaria Corona Johannes Schumacher Johannes Breidenbach Yang Su Lauri Mehtätalo Saverio FranciniAbstract
This data article presents a multi-source dataset of satellite-based auxiliary data designed for forest modelling and monitoring. The dataset integrates annual medoid composites derived from Sentinel-1, Sentinel-2, and Landsat imagery, together with spectral indices, Landsat-based 3I3D change metrics, forest mask and forest type layers, and terrain variables derived from the Copernicus GLO-30 DEM, offering comprehensive information on forest cover, spectral behavior, and change metrics. It provides harmonized predictors across seven European countries, ensuring consistency, scalability, and ease of use for researchers developing or validating models to understand forest dynamics and estimate forest-related variables such as biomass or canopy recovery. A curated subset of the dataset is distributed via Zenodo, along with direct public access links to the complete multi-terabyte archive. The data support applications in forest biodiversity conservation, carbon monitoring, biomass modelling, and climate-change impact assessment.
Authors
Johannes Schumacher Alessandro Cescatti Gherardo Chirici Giovanni D’Amico Saverio Francini Johannes Hertzler Lauri Mehtätalo Gert-Jan Nabuurs Mats Nilsson Juho Pitkänen Johannes BreidenbachAbstract
The availability of reliable ground-truth data is one of the main bottlenecks for improving high-resolution forest attribute maps from Earth observation data. This is underpinned by the European Union (EU) Forest Strategy for 2030 that underscores the need for harmonized, cross-border forest resource assessments that integrate both remote sensing and field-based National Forest Inventory (NFI) data. However, confidentiality constraints on NFI plot coordinates present a significant barrier to aligning these datasets, thereby limiting the development of unified forest monitoring systems that can fully leverage the potential of Earth Observation data. To overcome these data-sharing limitations we explored the effectiveness of a privacy-enhancing technique, known as Federated Learning (FL), that is a form of distributed computing aimed at preserving the privacy and confidentiality of data owned by different organizations. This methodology has been tested for the collaborative modelling and mapping of forest timber volume across four European countries: Norway, Sweden, Finland, and Italy. We employed a time-series convolutional neural network (CNN) architecture tailored to integrate 40 years of Landsat or 7 years of Sentinel imagery and terrain variables with harmonized NFI data from more than 85,000 sample plots. This model architecture was used for the FL approach and compared to traditional country-specific and centralized modelling strategies. FL models achieved predictive performances comparable to the traditional models, which proofs the effectiveness of the proposed approach. Centralized or global models showed slightly reduced performance compared to the national models, highlighting the value of fine-tuning with local ground-truth data. By aligning with the EU’s forest monitoring objectives, FL facilitates the generation of harmonized models and maps of forest features, like timber volume and biomass, that are critical to support evidence-based forest policy and management. The findings underscore the potential of FL to transform collaborative environmental monitoring, particularly in domains where data confidentiality and interoperability are critical.
Authors
Simone Bianchi Cornelia Roberge Johannes Schumacher Johannes Breidenbach Kari T. Korhonen Harri MäkinenAbstract
Sustainable forest management needs growth models. Few studies have explored regional models in Fennoscandia despite similar conditions and challenges. We examined the feasibility of regional models for basal area increment of Norway spruce (Picea abies (L.) Karst.), Scots pine (Pinus sylvestris L.), and birch (Betula pendula Roth. and Betula pubescens Ehrh.). We compiled over 880,000 growth observations and estimated competition indices, climate variables, and site fertility classes by integrating data from recent National Forest Inventories (2004–2023) in Finland, Norway, and Sweden. Using Random Forest models, we identified the main growth drivers across countries (tree size, accumulated temperature sum, latitude, competition, and site fertility), with minor differences in their responses across countries. However, periodic NFI measurements could not capture the effect of additional climate variables. Using species-specific nonlinear mixed models, we demonstrated that predictive regional models can be fitted using those main drivers. Although we achieved only moderate predictive performance (Weighted Absolute Percentage Error of 45–71%, depending on the species and country), there were no residual geographical biases. The results confirm the potential of Fennoscandian growth models to address shared challenges. Future work should better account for site fertility, integrate process-based approaches for climate responses, and carry out independent validation.
