A5041699825- Flood Risk Assessment and Management
- Hydrology and Watershed Management Studies
- Reservoir Engineering and Simulation Methods
- 3D Modeling in Geospatial Applications
- Anomaly Detection Techniques and Applications
- Hybrid Renewable Energy Systems
- Hydrology and Drought Analysis
- Remote Sensing and LiDAR Applications
- Renewable Energy and Sustainability
- Hydrological Forecasting Using AI
- 3D Surveying and Cultural Heritage
- Integrated Energy Systems Optimization
- Advanced Image Fusion Techniques
- Atmospheric and Environmental Gas Dynamics
- Spacecraft and Cryogenic Technologies
- Tropical and Extratropical Cyclones Research
- Groundwater and Watershed Analysis
- Image Processing and 3D Reconstruction
- Remote-Sensing Image Classification
- Fire Detection and Safety Systems
- Fire effects on ecosystems
- Remote Sensing in Agriculture
Leibniz University Hannover
2023
GFZ Helmholtz Centre for Geosciences
2023
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
2021-2023
Leibniz Institute for Research on Society and Space
2020
TU Bergakademie Freiberg
2020
Deutsches Bergbau-Museum Bochum
2020
Ruhr University Bochum
2020
Delft University of Technology
2018
Automated flood detection using earth observation data is a crucial task for efficient disaster management. Current solutions to identify flooded areas usually rely on calculating the difference between new observations and static, pre-calculated water extents derived by either single acquisitions or timely aggregated products. Such datasets, however, lack representation of real-world seasonality short-term changes in trend. In this paper we present complete workflow automatically detect...
This study introduces the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S1S2-Water</i> dataset – a global reference for training, validation and testing of convolutional neural networks semantic segmentation surface water bodies in publicly available Sentinel-1 Sentinel-2 satellite images. The consists 65 triplets images with quality checked binary mask. Samples are drawn globally on basis tile-grid (100 x 100 km) under consideration...
Abstract 3D indoor navigation in multi‐story buildings and under changing environments is still difficult to perform. models of are commonly not available or outdated. point clouds turned out be a very practical way capture interior spaces provide notion an empty space. Therefore, pathfinding rapidly emerging. However, processing raw can expensive, as these semantically poor unstructured data. In this article we present innovative octree‐based approach for the purpose pathfinding. We...
The 2022 hydrological drought in Europe was a significant event that resulted widespread water shortages and economic disruption. low levels had implications for supply chains, transport capacity quality. In this study, we used fully automated, neural-network based processing chain to semantically segment Sentinel-2 data. originally developed flood detection. To map changes surface-water extent during the drought, compared reference masks of previous two years with summer 2022.Our results...
A key factor in successful flood mapping is the fast and easy access to water extent information at normal, non-flood conditions. In this study, we propose a fully automated scalable methodology for generating publishing on permanent seasonal surface by leveraging cloud technologies such as Docker Kubernetes. Products can be computed global scale made accessible free of cost via standardized interfaces. With approach, disaster response community benefits from data flexible integration into...
Abstract. Cloud and cloud shadow segmentation is a crucial pre-processing step for any application that uses multi-spectral satellite images. In particular, time-critical disaster applications, require accurate immediate masks while being able to adapt possibly large variations caused by different sensor characteristics, scene properties or atmospheric conditions. This study introduces the newly developed open-source Python package ukis-csmask in Segmentation with performed pre-trained...
<p>This study introduces the S1S2-Water dataset – a global reference for training, validation and testing of convolutional neural networks semantic segmentation surface water bodies in publicly available Sentinel-1 Sentinel-2 satellite images. The consists 65 triplets images with quality checked binary mask. Samples are drawn globally on basis tile-grid (100 x 100 km) under consideration predominant landcover availability bodies. Each sample is complemented metadata Digital Elevation...
<p>This study introduces the S1S2-Water dataset – a global reference for training, validation and testing of convolutional neural networks semantic segmentation surface water bodies in publicly available Sentinel-1 Sentinel-2 satellite images. The consists 65 triplets images with quality checked binary mask. Samples are drawn globally on basis tile-grid (100 x 100 km) under consideration predominant landcover availability bodies. Each sample is complemented metadata Digital Elevation...
&lt;p&gt;Disastrous wildfires have occurred in many parts of the world during last two years (2019 and 2020), most notably South America, Australia, United States, regions north polar circle. Such extreme wildfire events pose a pervasive threat to human lives property thus been widely recognized global media. This study focusses on large-scale developments fire activity. It investigates occurrence burnt areas regarding several relevant parameters, namely extent, severity seasonality....