A5079670451- Remote Sensing and LiDAR Applications
- Automated Road and Building Extraction
- Galaxies: Formation, Evolution, Phenomena
- Astronomy and Astrophysical Research
- Stellar, planetary, and galactic studies
- Dark Matter and Cosmic Phenomena
- Cryospheric studies and observations
- Cosmology and Gravitation Theories
- Video Surveillance and Tracking Methods
- Gamma-ray bursts and supernovae
- Innovation and Knowledge Management
- Forest Ecology and Biodiversity Studies
- Climate change and permafrost
- Landslides and related hazards
- Atmospheric Ozone and Climate
- Atmospheric chemistry and aerosols
- University-Industry-Government Innovation Models
- Arctic and Antarctic ice dynamics
- Atmospheric and Environmental Gas Dynamics
- Advanced Neural Network Applications
- Forest ecology and management
- Remote Sensing in Agriculture
- Business Strategy and Innovation
- Soil Moisture and Remote Sensing
- Scientific Research and Discoveries
Science and Technology Corporation (Norway)
2020-2023
University of Nottingham
2010-2013
Abstract European Community (EC) Horizon-funded projects and Earth Observation-based Consortia aim to create sustainable value for Space, Land, Oceans. They typically focus on addressing Sustainable Development Goals (SDGs). Many of these (e.g. Commercialization Innovation Actions) have an ambitious challenge ensure that partners share core competencies simultaneously achieve technological commercial success sustainability after the end EC funds. To this challenge, Horizon must a proper...
Estimating building footprint maps from geospatial data is vital in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence segmentation maps, offering the promise of precise extraction without extensive post-processing. However, these methods face challenges generalization label efficiency, particularly remote sensing, where obtaining accurate labels can be both expensive time-consuming. To address challenges, we...
Faint fuzzies are metal-rich apparently-old star clusters with unusually large radii (7-15 pc), found mostly in S0 galaxies, whose source remain obscure. To identify their origins, we compare planetary nebulae and neutral hydrogen faint fuzzy positions line-of-sight velocities NGC1023. In this way, rule out scenarios which these objects associated an on-going merger or a spheroid population Their kinematics indistinguishable from the stellar disk galaxy, conclude that most likely just...
Various laboratory-based experiments are underway attempting to detect dark matter directly. The event rates and detailed signals expected in these depend on the phase space distribution sub-milliparsec scales. These scales many orders of magnitude smaller than those that can be resolved by conventional N-body simulations, so one cannot hope use such tools investigate effect mergers history Milky Way phase-space structure probed current experiments. In this paper we present an alternative...
Direct detection of dark matter on the Earth depends crucially its density and velocity distribution a milliparsec scale. Conventional N-body simulations are unable to access this scale, making development other approaches necessary. In paper, we apply method developed by Fantin, Merrifield Green in 2008 cosmologically based merger tree, transforming it into useful instrument reproduce analyse history Milky Way-like system. The aim model is investigate implications any ultrafine structure...
Measuring the mass balance of ice sheets is important with respect to understanding among others sea level rise, glacier dynamics, global ocean circulation and marine ecosystems. One parameter surface melt, which can be estimated from different satellite data sources. In this study we investigate potential utilizing machine learning techniques for CryoSat-2 (CS2) radar altimeter waveform classification in order derive melt information. Training derived by spatio-temporally matching CS2...
Precision building detection is a difficult challenge because resolution, lighting conditions, and image quality greatly influence the performance of machine learning models. Additionally, types, settlement structure, road soil color texture, vegetation, car types can also affect segmentation, making solutions local or regional. In this paper, we describe solution for MapAI submitted by ATELIER team. We focused on two primary parts: data processing loss functions. Our main insights were that...
Dark matter plays a fundamental role in theories of formation and evolution galaxies, so every attempt to model galaxy has consider the presence dark halos. Moreover, mergers accretions appear be driving mechanisms determining present day properties galaxies. Our project studies ultra‐fine distribution Milky Way implications for next generation particle detectors. We have developed halo Way‐like galaxy. The signals expected lab‐based detection experiments depend on phase‐space submilliparsec...
During the past 20 years, numerous stellar streams have been discovered in both Milky Way and Local Group. These tidally torn from orbiting systems, which suggests that most of them should roughly trace orbit their progenitors around Galaxy. As a consequence, they play fundamental role understanding formation evolution our This project is based on possibility applying technique developed by Binney 2008 to various tidal overdensities The aim develop an efficient method constrain Galactic...
Tree species mapping of Norwegian production forests is a time-consuming process as forest associations largely rely on manual interpretation earth observation data. Deep learning based image segmentation techniques have the potential to improve automated tree classification, but major challenge limited quality and availability training Semi-supervised could alleviate need for label weak supervision enables handling coarse-grained noisy labels. In this study, we evaluated added value...
Estimating building footprint maps from geospatial data is of paramount importance in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence segmentation maps, offering the promise precise extraction without extensive post-processing. However, these methods face challenges generalization label efficiency, particularly remote sensing, where obtaining accurate labels can be both expensive time-consuming. To address...
Background: The mapping of tree species within Norwegian forests is a time-consuming process, involving forest associations relying on manual labeling by experts. process can involve both aerial imagery, personal familiarity, or on-scene references, and remote sensing data. state-of-the-art methods usually use high resolution imagery with semantic segmentation methods. Methods: We present deep learning based classification model utilizing only lidar (Light Detection And Ranging) images are...
Abstract During the past 20 years, numerous stellar streams have been discovered in both Milky Way and Local Group. These tidally torn from orbiting systems, which suggests that most should roughly trace orbit of their progenitors around Galaxy. As a consequence, they play fundamental role understanding formation evolution our This project is based on possibility applying technique developed by Binney to various tidal overdensities The aim develop an efficient method constrain Galactic...
<p>European UVN satellite missions deliver global measurements for air quality and climate applications from Low Earth Orbit (LEO) satellites since over two decades. Currently we have in the morning data GOME-2 on three MetOp early afternoon OMI/Aura TROPOMI/Sentinel-5 Precursor.</p><p>The temporal barrier imposed by LEO satellites, providing only one daily observation, can be broken using Geostationary Equatorial (GEO) satellites. The Sentinel-4...