Find Academic Supervisors

Kasper Green LarsenView profile

Professor

• Machine Learning
• Theoretical Computer Science
• Algorithms and Data Structures
• +3 more

Kasper Green Larsen is a Professor in the Department of Computer Science at Aarhus University. His research focuses on theoretical computer science, machine learning, algorithms, and data structures. He has made significant contributions to boosting algorithms, PAC learning theory, and computational geometry. His work often bridges algorithm design with complexity theory, addressing challenges in optimization, memory efficiency, and lower bounds analysis. Key research areas include: Algorithmic Learning Theory (e.g., boosting, bagging, and PAC learners) Data Structure Design (e.g., invertible Bloom tables, succinct representations) Computational Complexity (e.g., lower bounds for dynamic and oblivious algorithms) Geometric Algorithms (e.g., hierarchical searching, range queries) Recent publications emphasize foundational advancements in learning theory (e.g., optimal weak-to-strong learning) and data efficiency (e.g., memory-reduced Bloom filters). His work frequently appears in top conferences like IJCAI, ICALP, and SODA, reflecting rigorous theoretical contributions with practical implications.

Ali LashgariView profile

Research Fellow

• Geotechnical Engineering
• Seismic Hazards
• Offshore Foundations
• +5 more

Ali Lashgari is a Marie Skłodowska-Curie Postdoctoral Research Fellow at Aalborg University's Department of the Built Environment (Faculty of Engineering and Science). He holds a PhD in Geotechnical Engineering from Semnan University (2019) and serves as a visiting researcher at Hong Kong University of Science and Technology. His research focuses on seismic hazards, offshore energy infrastructure resilience, and probabilistic geotechnical analysis. Education: PhD in Geotechnical Engineering, Semnan University (2019) MSc in Geotechnical Engineering, Semnan University (2013) BSc in Civil Engineering (not specified) Research Interests: Development of predictive models for geohazards (e.g., submarine landslides, liquefaction), offshore foundation resilience, and probabilistic analysis of seismic risks. His work integrates numerical modeling (e.g., DEM-FEM), machine learning, and big data analytics for hazard assessment frameworks. Awards: Marie Skłodowska-Curie Postdoctoral Fellowship (2023) Grants & Projects: PRO-SLIDE: EU-funded project (2023–ongoing) for offshore energy infrastructure resilience against seismic submarine landslides (PI) EU-COST Action CA23155: Pan-European network on ocean tribology (participant) Professional Activities: Founder of Intelligent Environmental Risks Analyzers (2016) Membership in AGU, DFI, GEER, IGS, and IRCEO Lab/Team Affiliation: Risk, Resilience, Safety, and Sustainability of Systems Research Group at Aalborg University.

Chenjuan GuoView profile

Associate Professor

• Machine Learning
• Data Engineering
• Spatio-temporal Data Analysis
• +4 more

Chenjuan Guo is an Associate Professor at the Department of Computer Science, Aalborg University, within The Technical Faculty of IT and Design. She is affiliated with the Data Engineering, Science and Systems group and the AI for the People initiative, and is part of the Daisy - Center for Data-intensive Systems. Her research focuses on machine learning, data engineering, spatio-temporal data analysis, and time series forecasting. Key projects include the Villum Foundation-funded 'Explainable AI for Complex Microbial Community Interactions and Predictions' (2021-2024) and the Astra project on time series analytics in spatial networks (2018-2021). Her research interests span representation learning, autoencoders, path representation, outlier detection, trajectory data analysis, and time series modeling. She has supervised 3 PhD students and contributed to over 60 publications, with a recent emphasis on transformer-based forecasting, neural architecture search, and continuous learning frameworks for spatio-temporal data. Her work bridges theoretical advancements with practical applications in environmental science, cloud computing, and urban mobility systems. Key achievements include developing frameworks like AutoCTS++ for automated time series forecasting and LightGTS for lightweight models. She actively collaborates internationally, contributing to conferences like ECML PKDD and CVPR. Her research is supported by grants from the Villum Foundation and other institutions.

Thomas Martini JørgensenView profile

Researcher

• Machine Learning
• Deep Learning
• Big Data
• +3 more

Thomas Martini Jørgensen is a Senior Researcher at the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU). His work primarily focuses on machine learning applications in telecommunication networks and industrial processes. Key Research Areas: Machine Learning, Deep Learning, Network Impairments, Fault Detection Collaborations: Active collaborations in AI for cable broadband networks and optical network diagnostics Recent research involves integrating operations research with deep learning for network topology reconstruction and applying conditional diffusion models for fault detection in optical networks. His work spans both theoretical and applied domains, with a focus on industrial applications. He supervises PhD projects including: Anomaly Detection in Cable Broadband Networks Machine Learning Applications in Field Service His publications demonstrate expertise in convolutional neural networks for flocculation analysis and geomechanical modeling of fracture networks in petroleum engineering.

Mateja NovakView profile

Assistant Professor

• Model Predictive Control
• Power Electronics
• Multilevel Converters
• +6 more

Mateja Novak is an Assistant Professor at AAU Energy, Aalborg University, Denmark, within the Department of Applied Power Electronic Systems under the Faculty of Engineering and Science. Her research focuses on model predictive control, multilevel converters, machine learning, and reliability of power electronic systems, contributing to sustainable energy systems and renewable energy integration. She holds a Ph.D. from Aalborg University (2020) and an M.Sc. from Zagreb University (2014). Previously, she was a Postdoc at AAU Energy (2020-2023) and a visiting researcher at Kiel University (2018) and Danfoss (2023). Notable achievements include the EPE Outstanding Young EPE Member Award (2019) and 2nd place in the 2021 IEEE-IES Student and YP Competition. Her work spans projects like ALL2GaN (2023-2026) and AI-Power (2022-2027), addressing GaN IC solutions and AI-driven power electronics advancements. She is actively involved with IEEE societies including the Power Electronics Society and IEEE Women in Engineering. Her research outputs emphasize control strategies for power electronics, reliability analysis, and optimization techniques. Key areas of exploration include thermal stress balancing in converters, statistical model checking, and multiobjective control algorithms. Collaborations with industry partners like Danfoss and academic institutions like Kiel University underscore her interdisciplinary approach to advancing power electronics technology.

Alvaro TorralbaView profile

Associate Professor

• Symbolic Search
• Artificial Intelligence
• Machine Learning
• +3 more

Alvaro Torralba is an Associate Professor in the Department of Computer Science at Aalborg University, Denmark, affiliated with the Technical Faculty of IT and Design. His research focuses on symbolic search, heuristic functions, and planning algorithms within artificial intelligence and machine learning. Notable projects include the ConAn initiative exploring contrastive analysis for state-space exploration. He has contributed extensively to classical planning, probabilistic planning, and automated planning competitions, earning awards such as the First Prize in the Agile Track of the 10th International Planning Competition (IPC’23). His work often bridges theoretical advancements with practical applications, including game-based network update synthesis and believable non-player character development. Research outputs include over 60 publications since 2011, with a focus on optimizing search algorithms and enhancing planning efficiency through techniques like operator-potential heuristics and bidirectional search strategies. His scientific contributions span algorithmic innovation, verification methodologies, and large-scale abstraction evaluation. Collaborations and datasets include foundational work on PDDL generators and pattern databases, with open-access resources available via Zenodo. As a program committee member and award-winning researcher, Torralba actively contributes to advancing the frontiers of AI planning and decision-making systems.

Henrik MadsenView profile

Professor

• Energy Systems
• Stochastic Processes
• Demand Response
• +7 more

Henrik Madsen is a Professor at the Department of Applied Mathematics and Computer Science, Technical University of Denmark (DTU). His work focuses on energy systems, stochastic processes, and mathematical modeling. He leads research in areas such as demand response in district heating, probabilistic forecasting, and integration of renewable energy sources. Madsen has supervised multiple PhD students and contributes to projects like the IEA DHC Annex TS9 and SEEDS initiative. His expertise includes statistical analysis, time series modeling, and data-driven approaches for energy systems. He actively engages in collaborative research on smart grids, thermal energy storage, and sustainable energy solutions. Education: Academic qualifications from DTU, though specific details are not provided in the text. Research Interests: Mathematical modeling of energy systems Probabilistic forecasting methodologies Integration of wind and solar power Dynamic modeling for district heating Data assimilation in hydrological systems Optimization of energy flexibility Publications & Trends: Recent works emphasize demand response strategies, district heating optimization, and machine learning tools like the nabqr Python package and evalprob4cast R package. His research bridges theoretical stochastic methods with practical applications in energy infrastructure. Grants & Projects: IEA DHC Annex TS9: Digitalization of district heating SEEDS: RES-integrated electrified heating systems Data-Driven Methods for Demand-Side Flexibility Labs/Teams: Collaborates with DTU's Dynamical Systems group and participates in interdisciplinary initiatives like the Frigg 2.0 energy system analysis framework.

• Distributed Systems
• Embedded Systems
• Real-Time Systems
• +3 more

Brian Nielsen is an Associate Professor at Aalborg University's Department of Computer Science, under The Technical Faculty of IT and Design. His research focuses on Distributed Systems, Embedded Systems, Real-Time Systems, Model Checking, IoT Networks, and Autonomous Vehicles. He has been actively involved in projects such as domOS (operating system for smart buildings), FED (Flexible Energy Denmark), and compositional verification of multicore avionics systems. His work emphasizes model-based validation, formal methods, and industrial applications, particularly in safety-critical systems. Recent research highlights include energy-efficient motion planning for autonomous vehicles, comparative analysis of network simulators, and sigfox-based IoT modeling. He has received awards including the Application Coordinator Pool and START funds (both in 2007). Key Projects: domOS, FED, compositional verification of multicore systems Grants: Multiple EU-funded projects (e.g., Horizon Europe) and industry collaborations Awards: Application Coordinator Pool (2007), START funds (2007) His publications span over 80 articles, with a focus on real-time systems, IoT interoperability, and model-driven development. He has advised two PhD students and has been actively involved in organizing international conferences and workshops.

Guangya YangView profile

Associate Professor

• Power System Stability
• Offshore Wind Energy
• Cyber-Physical Power Systems
• +7 more

Guangya Yang is an Associate Professor at the Department of Wind and Energy Systems, Technical University of Denmark (DTU), with expertise in power system stability, control, and protection of low-inertia systems, particularly in offshore wind applications. He has worked full-time as an electrical design and simulation specialist at Ørsted (2020-2021) and maintains active roles in IEEE, IEC standardization, and editorial work as lead editor for IEEE Access PES. PhD in Electrical Engineering (University of Queensland, 2008) Senior Member of IEEE Former expert member of European Technology & Innovation Platform for solar PV His research focuses on electromagnetic transient simulation, cyber-physical energy systems, and grid compliance for wind power plants. He leads the Horizon 2020 InnoCyPES project (€12m+ grants), training 15 early-stage researchers in cyber-physical energy systems. Key contributions include validating synchronous condensers for low-inertia systems and developing industry training programs on offshore wind control strategies. Coordinated Hardware-in-the-Loop test bench standards (IEC61400-21-5) Advances in grid-forming converter stability and fault ride-through assessment Developed digital twins for power grid validation Scientific Recognition: World’s Top 2% Scientists (Elsevier/Stanford, 2024) Advising & Grants: Supervises 5 PhD students in projects related to machine learning, digital twins, and predictive maintenance. Coordinates €12m+ in research grants, including Horizon 2020’s InnoCyPES. Labs & Collaborations: Works with Ørsted, industry partners, and international universities on offshore wind validation and digitalization.

Julian Antony QuickView profile

Researcher

• Wind Power
• Wind Turbine Engineering
• Compressed Air Motors
• +3 more

Julian Antony Quick is a Researcher at the Department of Wind and Energy Systems within the Technical University of Denmark . His work focuses on wind farm optimization, energy management, and market-driven renewable energy systems. Active research in wind farm control and market integration Specializes in hybrid power plant design and uncertainty quantification Contributes to UN Sustainable Development Goals through wind energy research His research explores advanced optimization techniques for wind resource assessment, turbine design, and revenue maximization in electricity markets. Key areas include: Compressed air energy storage integration Wind farm layout optimization Surrogate-based system modeling Dynamic energy management strategies While not explicitly listed, his collaborative projects suggest active involvement in PhD supervision and industry partnerships across Europe. His recent publications demonstrate a strong focus on translating technical advances into economic benefits through: Market-aware wind farm design Data-driven flow control Hybrid system efficiency improvements SDG-aligned sustainable energy solutions

Martin DrewsView profile

Professor

• Climate Change
• Climate Economics
• Risk Management
• +6 more

Martin Drews is a Professor at the Department of Technology, Management and Economics at the Technical University of Denmark (DTU). His research focuses on climate economics, risk management, and energy policy with an emphasis on adaptation to climate change. He is actively involved in projects addressing compound climate extremes, flood risk assessment, and decision-making frameworks under uncertainty. Key research areas include reinforcement learning applications in climate adaptation, coastal flood modeling, and interdisciplinary approaches to disaster resilience. He co-leads initiatives like the Horizon-RIA ACCRUE project and supervises multiple PhD students investigating climate policy, multi-hazard risk assessment, and compound event dynamics. Recent studies emphasize the intersection of machine learning with climate adaptation, statistical methods for extreme event analysis, and the water-energy nexus. His work contributes to UN Sustainable Development Goals related to climate action, resilient infrastructure, and sustainable cities. Dr. Drews collaborates internationally on projects such as compound event modeling in Denmark and Baltic Sea region studies. He has authored over 99 publications, with recent work highlighted in journals like Natural Hazards and Earth System Sciences and Bulletin of the American Meteorological Society .

Tue HerlauView profile

Associate Professor

• Bayesian Methods
• Complex Networks
• Brain Imaging Data Analysis
• +3 more

Tue Herlau is an Associate Professor at the Department of Applied Mathematics and Computer Science, Cognitive Systems, within the College of Engineering at Technical University of Denmark. His research focuses on modeling complex networks using Bayesian methods, particularly applied to brain imaging data. He explores multiscale structures in networks (ranging from individual nodes to large-scale temporal dynamics) and causal inference in social and biological systems. Education : Bachelor in Physics and Mathematics (University of Copenhagen), Masters in Informatics (DTU) Recent publications highlight work on generative AI for educational psychology, causal probability trees, Bayesian neural network training, and moral reinforcement learning. Key collaborations span institutions in Denmark and international partners in AI and neuroscience research. He supervises students in probabilistic methods and machine learning applications, including a 2019-2020 Master project on prognostics for carbon/epoxy composites. His network shows strong engagement with computational science, relational databases, and formal concept analysis.

Nico LangView profile

Assistant Professor

• Computer Vision
• Machine Learning
• Remote Sensing
• +4 more

Nico Lang is an Assistant Professor at the University of Copenhagen's Department of Computer Science, associated with the Pioneer Centre for AI and Global Wetland Centre. He holds a PhD from ETH Zurich where he developed methods for global forest structure mapping. His research bridges computer vision, machine learning, and remote sensing to address environmental challenges like deforestation monitoring and climate change mitigation. Lang's research focuses on: Developing probabilistic deep learning models for global canopy height estimation Advancing open-set recognition under adversarial conditions Creating multi-modal representation learning frameworks for geospatial data Applying computer vision to biodiversity monitoring and conservation His work frequently appears in top venues like Nature, CVPR, and ECCV. His publications show strong emphasis on: environmental applications of AI, uncertainty-aware deep learning, and global-scale geospatial analysis. Recent work explores vision-language models and fine-grained open-set recognition. Awards & Honors: Culmann Prize for outstanding doctoral thesis (2023) Outstanding Reviewer for CVPR 2023 U.V. Helava Award for best paper in ISPRS Journal (2019) Associate PhD Fellow at Max Planck ETH Center (2018) Collaborations & Labs: Directs research at the intersection of computer vision and environmental science. Key affiliations include NASA GEDI mission, Swiss Federal Institute for Forest, Snow and Landscape Research, and the Pioneer Centre for AI. Organizes workshops like FGVC at CVPR and SSL4EO summer schools.

Jon SporringView profile

Professor

• Computer Science
• Mathematical Image Processing
• Medical Image Analysis
• +6 more

Jon Sporring is a Professor at the Department of Computer Science, University of Copenhagen, specializing in theoretical and applied image processing, stochastic geometry, and biomedical imaging. He leads research in mathematical and medical image analysis, computer graphics, and pattern recognition. Education: Ph.D. in Computer Science (1998), Master in Computer Science (1995), both from University of Copenhagen Affiliations: Pioneer AI section, Applied Geometry Lab, and Faculty of Science External Roles: Visiting professor at McGill University (2012-13), co-founder of DigiCorpus Aps (2012-16) His research integrates scale-space theory, statistical shape analysis, and advanced imaging techniques for applications in medical diagnostics, materials science, and neuroscience. Recent work focuses on 3D reconstruction, persistent homology for bias correction, and AI-driven biomedical analysis. Jon teaches computer science at all academic levels, currently offering courses in bioimaging, signal processing, and deep learning. He emphasizes collaborative projects with external partners and has held administrative roles including Vice-Chair for Research at DIKU. His 15 most recent publications reflect expertise in medical imaging, 3D modeling, and AI applications, with subfields spanning neurodegenerative disease analysis, mitochondrial ultrastructure, and multi-scale image processing. Articles demonstrate interdisciplinary impact across medicine, biology, and materials science.

Michele AlbanoView profile

Associate Professor

• Internet of Things (IoT)
• Energy Engineering
• Quality of Service (QoS)
• +5 more

Affiliations & Roles Michele Albano is an Associate Professor at the Department of Computer Science, Aalborg University, Denmark. He is affiliated with The Technical Faculty of IT and Design, focusing on research in IoT, Cyber-Physical Systems, and Edge Computing. He leads the Productive4.0 project (2017–2020), funded by Horizon Europe, addressing Industry 4.0 challenges in product lifecycle management. His work integrates formal verification tools like Uppaal with real-world applications in robotics, energy systems, and blockchain-based platforms. Research Interests Albano's research spans IoT architecture optimization , energy-efficient systems , and model-driven engineering . He develops tools for autonomous exploration algorithms (MAES), edge-cloud resource orchestration, and fault-tolerant computation offloading. His work bridges theoretical models (e.g., Uppaal SMC) with practical implementations in smart grids and robotic systems. Recent projects include blockchain-based crowdsourcing for machine learning and energy-aware thermal dynamics estimation in buildings. Collaborations & Impact He collaborates with the European Industry 6.0 community, contributing to the Arrowhead Framework for interoperable IoT systems. His research outputs include 112 publications, with 2025 highlights in human-inspired robotics and cognitive cloud frameworks. Media coverage in 2024–2025 highlights his work on green IT and secure API generation. Albano advises students on system modeling (e.g., ACSmt plugin development) and edge computing optimization. Labs & Teams His research group focuses on Cyber-Physical Systems and Smart Grids , with contributions to tools like RoutesMobilityModel and FlexHousing. He actively participates in workshops on New Trends in Software Architecture (SATrends '24) and IEEE conferences on Industrial Informatics.