Project: Research team and infrastructure upgrade to study the mechanism of conifer resistance to bark beetles in the changing climate: From Gene to Tree level.
Norway spruce susceptibility to the spruce bark beetle and an associated fungus -Effects of tree phenology, site conditions and seasonal variability.
Response of mature Norway spruce to experimental termalthermal and drought stress in relation to Ips typographus attack: Crown temperatures and sap flow.
Topographic distribution of bark beetle damage and measurements of tree vigour in tree and plot level, preliminary results from Koli National Park.
Simulating forest disturbances and their impacts on forests in a changing world.
Modeling the Impact of Drought on Spruce Bark Beetle Outbreaks Using the TANABBO II model.
Risk mapping of bark beetle attacks during drought.
Remote sensing of bark beetle - what can we see from space?
Forest disturbances across the European Alps: a landscape-scale analysis based on Landsat time series.
Dead spruce detection in Norway using Sentinel-2.
Advancements in autonomous drone technologies for bark beetle management.
Scalability of Deep Learning Models for Bark Beetle Infestation Detection: Addressing Domain Shift Across Diverse Study Areas.
Drone-based multiannual methods for bark beetle induced forest disturbance monitoring.
Spectral Signatures of Spruces Under Acute and Chronic Stress.
Early detection of Bark Beetles by Drone Images differs in Endemic and Epidemic Populations.
Lesson learned so far from the Swedish test site: what affects the bark beetle pre-emergence detection using drone imagery?
In this session, Dr. Kenji Ose will demonstrate nrt, which is a Python package designed for near real-time detection of changes in spatio-temporal datasets, with a particular focus on monitoring forest disturbances from satellite image time series. It offers a standardized API inspired by scikit-learn, ensuring seamless interoperability and comparison across various state-of-the-art monitoring algorithms. Optimized for rapid computation, nrt is suitable for operational deployment at scale. This package is an essential tool for researchers and practitioners aiming for timely and efficient monitoring, contributing to climate change mitigation, biodiversity conservation, and natural heritage preservation.
Find more info on https://github.com/ec-jrc/nrt and https://github.com/kenoz/NRT-tutorial
Please get ready to use Python to follow our hands-on exercise.
In this session, Dr. Reza Belaghi will demonstrate how generalized linear models can be used to analyze environmental factors of forest damage risks. We will learn about specifying generalized linear models including conditions and assumptions, selecting an appropriate linear model for a given problem, carrying out an analysis based on a generalized linear model in the statistical software R, interpreting and evaluating results correctly and drawing reasonable conclusions, and clearly and concisely communicating results and conclusions. Please get ready to use R to follow our hands-on exercise.