A5041583196- Fish Ecology and Management Studies
- Marine and fisheries research
- Methane Hydrates and Related Phenomena
- Arctic and Antarctic ice dynamics
- Atmospheric and Environmental Gas Dynamics
- Fish Biology and Ecology Studies
- Environmental Monitoring and Data Management
- Advanced Neural Network Applications
- Marine and coastal ecosystems
- Advanced Vision and Imaging
- Aquatic Ecosystems and Phytoplankton Dynamics
- Marine and coastal plant biology
- Climate change and permafrost
- Isotope Analysis in Ecology
- Aquatic Invertebrate Ecology and Behavior
- Advanced Image and Video Retrieval Techniques
- Oceanographic and Atmospheric Processes
- Marine Biology and Ecology Research
- Water Quality Monitoring Technologies
- Marine Bivalve and Aquaculture Studies
- Recommender Systems and Techniques
- Cell Image Analysis Techniques
- Image Retrieval and Classification Techniques
- Scientific Computing and Data Management
- Coastal wetland ecosystem dynamics
Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung
2013-2024
GEOMAR Helmholtz Centre for Ocean Research Kiel
2024
Medical University of Graz
2024
École Polytechnique Fédérale de Lausanne
2023
Swiss Data Science Center
2023
ETH Zurich
2023
Universitätsklinik Balgrist
2023
Constructor University
2020-2022
Computing Center
2020
University of Freiburg
2014-2018
Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not among the tasks CNNs succeeded at. In this paper we construct which are capable solving optical problem as supervised learning task. We propose and compare two architectures: generic architecture another one including layer that correlates feature vectors at different image locations. Since existing ground...
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by large synthetically generated dataset. The present paper extends concept via networks to disparity scene estimation. To this end, we propose three synthetic stereo video datasets sufficient realism, variation, size train Our are first large-scale enable training evaluating methods. Besides...
Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such follows mostly the supervised paradigm, where sufficiently many input-output pairs are required training. Acquisition large training sets is one key challenges, when approaching a new task. In this paper, we aim generic feature and present an approach network using only unlabeled data. To end, train...
There is large consent that successful training of deep networks requires many thousand annotated samples. In this paper, we present a network and strategy relies on the strong use data augmentation to available samples more efficiently. The architecture consists contracting path capture context symmetric expanding enables precise localization. We show such can be trained end-to-end from very few images outperforms prior best method (a sliding-window convolutional network) ISBI challenge for...
Dental radiography plays an important role in clinical diagnosis, treatment and surgery. In recent years, efforts have been made on developing computerized dental X-ray image analysis systems for usages. A novel framework objective evaluation of automatic algorithms has established under the auspices IEEE International Symposium Biomedical Imaging 2015 Bitewing Radiography Caries Detection Challenge Cephalometric Image Analysis Challenge. this article, we present datasets, methods results...
Latest results indicate that features learned via convolutional neural networks outperform previous descriptors on classification tasks by a large margin. It has been shown these still work well when they are applied to datasets or recognition different from those were trained on. However, like SIFT not only used in but also for many correspondence problems rely descriptor matching. In this paper we compare various layers of nets standard descriptors. We consider network was ImageNet and...
Abstract. The Coastal Observing System for Northern and Arctic Seas (COSYNA) was established in order to better understand the complex interdisciplinary processes of northern seas coasts a changing environment. Particular focus is given German Bight North Sea as prime example heavily used coastal area, Svalbard an coast that under strong pressure due global change.The COSYNA automated observing modelling system designed monitor real-time conditions provide short-term forecasts, data, data...
In the next decade pressures on ocean systems and communities that rely them will increase as multiple stressors of climate change, food security human activities start to impact. Our ability manage sustain our oceans depend data we collect information knowledge generated. Much uptake this be outside domain, for example by policy makers, local Governments, custodians other organizations, so it is imperative democratize or open access use data. This paper looks at how technologies, scoped...
The Marine Stations Helgoland and Sylt are permanent coastal stations in the German Bight operated as one joint research infrastructure by Alfred Wegener Institute Helmholtz Centre for Polar Research (AWI). Using both stations, south-west region of North Sea its ecosystem features tightly monitored via ecological time series, which recorded made available to government offices, professional associations, institutes world-wide. a hub national transnational access guest researchers visiting...
Abstract The Arctic archipelago of Svalbard is a hotspot global warming and many fjords experience continuous increase in seawater temperature glacial melt while sea‐ice cover declines. In 1996/1998, 2012–2014, 2021 macroalgal biomass species diversity were quantified at the study site Hansneset, Kongsfjorden (W‐Spitsbergen) order to identify potential changes over time. 2021, we repeated earlier studies by stratified random sampling (1 × 1 m 2 , n = 3) along sublittoral depth transect (0,...
With 9 figures and 5 tables in the text Abstract: The spatial distribution patterns of habitat use littoral fish species Lake Constance were studied using electric fishing trammel net sampling to assess abundance biomass three depth strata at six different sites within zone. Distribution differences among found be often more pronounced than sites. Juvenile chub tLeuciscus cephalus i dace leuciscusi most abundant shallow areas <50 cm water with maxima 54.9 29.2 ind . 100 m- 2. bream (Abramis...
The Helmholtz Association's Research Field Earth and Environment the German Marine Alliance (DAM)—a partnership between federal government, five northern states, 25 research-oriented organizations—have come together to connect distributed data infrastructures of their members partners. Their collaboration aims create a Data Ecosystem, facilitating centralized access marine information. This ecosystem will provide open global FAIR (Findable, Accessible, Interoperable, Reusable) from science....
Changes in the water level of lakes, either natural or man-made, are important environmental perturbations for eulittoral benthic fish communities. In outdoor mesocosm experiments, we tested effects decreasing shelter availability due to autumn lake-level decrease on behavior and growth two littoral dwellers, juvenile burbot stone loach. The species showed significantly different changes when decreased. Burbot built up a distinct hierarchy became sparse, with larger being more successful...
Nutrient and carbon dynamics within the river-estuary-coastal water systems are key processes in understanding flux of matter from terrestrial environment to ocean. Here, we analysed those by following a sampling approach based on travel time an advanced calculation nutrient fluxes tidal part. We started with nearly Lagrangian river (River Elbe, Germany; 580 km 8 days). After subsequent investigation estuary, followed plume raster German Bight (North Sea) using three ships simultaneously. In...
Phytoplankton biomass and composition was investigated in a high Arctic fjord (Kongsfjorden, 79˚N, 11˚40'E) using year round weekly pigment samples collected from October 2013 to December 2014. In addition, phytoplankton dynamics supplemented with physical chemical characteristics of the 2014 spring bloom (April –June 2014) were assessed two locations Kongsfjorden. The goal elucidate effects Atlantic advection on spatial chlorophyll-a (chl-a) taxonomic composition. Chl-a declined during...