A5006751862- Remote Sensing and LiDAR Applications
- Forest ecology and management
- Remote Sensing in Agriculture
- Forest Ecology and Biodiversity Studies
- Urban Heat Island Mitigation
- Power Systems and Technologies
- Vehicle Dynamics and Control Systems
- Wood and Agarwood Research
- Marine and coastal ecosystems
- Forest Insect Ecology and Management
- Remote-Sensing Image Classification
- Traffic Prediction and Management Techniques
- Software System Performance and Reliability
- Species Distribution and Climate Change
- Network Traffic and Congestion Control
- Real-time simulation and control systems
- Calibration and Measurement Techniques
- Wildlife-Road Interactions and Conservation
Leipzig University
2024-2025
Center For Remote Sensing (United States)
2025
German Research Centre for Artificial Intelligence
2024
Center for Scalable Data Analytics and Artificial Intelligence
2024
Freie Universität Berlin
2020
The increasing frequency and intensity of droughts heat waves driven by climate change have led to a significant increase in tree mortality worldwide. However, the lack accurate consistent data on location, timing, species, structure dead trees across vast geographical areas limits our understanding climate-induced mortality. Furthermore, standing dying are crucial indicators forest health biodiversity but often overlooked existing resource mapping systems.To address this, we present novel...
Tree mortality rates are rising across many regions of the world. These driven by complex interplay abiotic and biotic factors, including global warming, climate extremes, pests, pathogens, other environmental stressors. Despite urgency understanding these dynamics, critical gaps remain in our ability to determine where trees dying, why they predict future hotspots. knowledge primarily caused missing data on tree events. Ground-based observations, such as national forest inventories, often...
In the wake of extreme heat and drought events, excess tree mortality is increasing globally. While forest inventories provide valuable data for geolocating mortality, they are sparse do not identify individual mortality. Aerial captured by drones airplanes precise centimeter-scale imagery that can be used to map fractional cover. The deadtrees.earth platform provides a comprehensive archive annotated high-resolution orthoimages around globe different ecosystems biomes. By using from...
Accurate and scalable tree species identification remains a critical challenge for global forest monitoring management. Despite the increasing availability of remotely sensed data, lack standardized, high-quality ground truth datasets limits potential supervised machine learning models in capturing diversity ecosystems across different environmental geographic contexts. Prior studies have highlighted need global-scale, high-resolution to develop robust algorithms capable ecosystems.Towards...
Pinpointing autonomous systems which deploy specific inter-domain techniques such as Route Flap Damping (RFD) or Origin Validation (ROV) remains a challenge today. Previous approaches to detect per-AS behavior often relied on heuristics derived from passive and active measurements. Those heuristics, however, lacked accuracy imposed tight restrictions the measurement methods.
Terrestrial surface processes exhibit distinctive spectral signatures captured by optical satellites. Despite the development of over two hundred indices (SIs), current studies often narrow their focus to individual SIs, overlooking broader context land processes. This project seeks understand holistic features Sentinel-2 based SIs and relationships with human impact overall dynamics. To address this, we propose an AI-driven approach that synthesises derived from Sentinel data through...
Abstract. The Sentinel-2 (S2) mission from the European Space Agency’s Copernicus program provides essential data for Earth surface analysis. Its Level-2A products deliver high-to-medium resolution (10–60 m) reflectance (SR) through MultiSpectral Instrument (MSI). To enhance accuracy and comparability of SR data, adjustments simulating a nadir viewing perspective are essential. These corrections address anisotropic nature variability in sun observation angles, ensuring consistent image...
Tree mortality has escalated worldwide in recent years due to climate warming and unprecedented drought events. However, mapping tree across forest ecosystems not yet been achieved. Aerial photos provide opportunities reveal the spatial spectral characteristics of canopy death at local landscape scales. In this work, we present a deep learning model for from aerial various forested Europe. This builds on baseline trained with data dead canopies California using sub-meter resolution allows...
Excess tree mortality in the wake of climate extremes has been observed globally. However, we still lack precise data on at global scale to understand respective drivers and spatiotemporal dynamics. The Sentinel-2 satellite fleet, equipped with MultiSpectral Instrument (MSI), covers entire earth average every five days spatial resolutions ranging from 10 m 60 m. Mapping globally diverse ecosystems requires equally reference data. Using distributed high-resolution aerial orthoimagery...
Excessive tree mortality rates prevail in many regions of the world. Understanding dynamics remains elusive as this multifaceted phenomenon is influenced by an interplay abiotic and biotic factors including, but not limited to, global warming, climate extremes, pests, pathogens, other environmental stressors. Earth observation satellites, coupled with machine learning, present a promising avenue to unravel map standing dead trees lay foundation for explaining underlying dynamics. However,...
The Sentinel-2 (S2) mission from the European Space Agency's Copernicus program provides essential data for Earth surface analysis. Its Level-2A products deliver high-to-medium resolution (10-60 m) reflectance (SR) through MultiSpectral Instrument (MSI). To enhance accuracy and comparability of SR data, adjustments simulating a nadir viewing perspective are essential. These corrections address anisotropic nature variability in sun observation angles, ensuring consistent image comparisons...
Abstract Excessive tree mortality is a global concern and remains poorly understood as it complex phenomenon. We lack temporally continuous coverage on data. Ground-based observations mortality, e.g ., derived from national inventories, are very sparse, not standardized spatially explicit. Earth observation data, combined with supervised machine learning, offer promising approach to map over time. However, global-scale learning requires broad training data covering wide range of...