Find Academic Supervisors

• Digital Soil Mapping
• Soil Organic Carbon
• Machine Learning Applications
• +3 more

Laura Poggio serves as a Research Associate at ISRIC - World Soil Information, which operates under Wageningen University & Research. Her work focuses on advancing digital soil mapping methodologies and global soil information systems through interdisciplinary research combining remote sensing, machine learning, and soil science. Her primary research interests include: Digital Soil Mapping at multiple scales (local to global) Soil Organic Carbon monitoring using satellite imagery Machine learning applications for soil property prediction Global soil information systems development (notably SoilGrids) Integration of remote sensing data with soil databases Analysis of her 15 most recent publications reveals strong emphasis on continental-scale soil monitoring systems, particularly using Sentinel-2 satellite data for soil organic carbon assessment across Europe. Her work consistently addresses methodological challenges in handling spatial uncertainty, integrating multi-source data, and developing scalable models applicable from local to global contexts. Key technological approaches include machine learning algorithms (particularly Random Forest), survival probability models for censored data, and multi-sensor remote sensing integration. Her research output demonstrates significant collaboration across European institutions through projects like EJP SOIL and contributions to the Global Soil Partnership. While no specific awards are documented in the available materials, her work shows substantial scholarly impact through high citation counts and dataset adoption. Dr. Poggio actively contributes to soil science through conference presentations and supervised research work, particularly focusing on operational implementation of digital soil mapping for environmental monitoring and policy support.

• Crowd Simulation
• Path Planning
• Real-time Simulation Software
• +3 more

Wouter van Toll is a Lecturer at the Academy for AI, Games & Media, specializing in crowd simulation and real-time systems. His research focuses on path planning, crowd behavior modeling, and fluid dynamics in agent-based simulations. He has contributed to advancing algorithms for microscopic crowd simulation and integrating techniques like Smoothed Particle Hydrodynamics (SPH) to handle extreme crowd densities. Key research interests include sketch-based interaction design for steering behaviors, navigation mesh optimization, and topological strategies for agent coordination. His work bridges computational methods with creative applications in game development and artificial intelligence. Received Best Paper Award Honorable Mention (2022) for his work on sketch-based steering behaviors in crowd simulation. Active collaborations in Europe and North America, particularly in crowd simulation software development. Publications span algorithmic advancements in crowd simulation, navigation systems, and interdisciplinary applications combining physics-based methods with agent-based models. Current research emphasizes real-time simulation efficiency and human-centered design tools for behavior specification.

Herke van HoofView profile

Associate Professor

• Reinforcement Learning
• Modular Reinforcement Learning
• Hierarchical Structures
• +5 more

Herke van Hoof serves as Associate Professor at the University of Amsterdam within the Informatics Institute, where he leads research in the AMLab at Science Park (Lab 42, L4.05). His academic journey spans from AI degrees at Groningen University through doctoral studies at TU Darmstadt under Professor Jan Peters to postdoctoral research at McGill University with Professors Joelle Pineau, Dave Meger, and Gregory Dudek. PhD: TU Darmstadt (2016), supervised by Prof. Jan Peters Postdoc: McGill University, Montreal AI Bachelor & Master: University of Groningen Van Hoof's research focuses on overcoming data inefficiency in reinforcement learning through modular and hierarchical approaches. His work explores how structured representations can enable knowledge transfer between tasks, improve learning efficiency, and facilitate applications in domains with complex state and action spaces. The lab investigates symmetry exploitation in multi-agent systems, gradient estimation techniques for discrete variables, and applications to combinatorial problem solving. His publication record shows consistent contributions to top AI venues including ICML, ICLR, NeurIPS, and JMLR over the past seven years. The research trajectory demonstrates evolution from foundational policy search methods toward increasingly sophisticated modular architectures, with recent emphasis on knowledge-assisted AI for critical infrastructure applications through the AI4REALNET project. Third place in ARC prize (Paper award) Van Hoof actively supervises PhD candidates and postdoctoral researchers, with current projects including human-robot collaboration using brain-computer interfaces (with Maryam Alimardani at VU) and interactive robot learning with flexible human input (through The Hybrid Intelligence Centre). His research receives support from multiple funding initiatives including the AI4REALNET project which focuses on applying AI to critical infrastructure systems. As co-organizer of the BeNeRL 2024 workshop and participant in the AI4REALNET consortium, van Hoof maintains strong connections with the broader European AI research community while directing the AMLab's research on modular reinforcement learning approaches.

Hendrik BaierView profile

Assistant Professor

• Artificial Intelligence
• Planning
• Search Algorithms
• +5 more

Hendrik Baier is an Assistant Professor in the Information Systems group at Eindhoven University of Technology (TU/e), where he joined in 2022. His research focuses on creating agents capable of succeeding in complex decision-making tasks to help human users solve real-world problems. His work spans planning for long-term goals, learning in unknown environments, and explainability of AI systems for effective human-AI interaction. Dr. Baier's research interests center on planning and search algorithms, reinforcement learning, and explainable AI systems. His work investigates how AI can think ahead and explain its reasoning process, particularly in sequential decision-making contexts. He applies these techniques to practical domains including logistics and transportation, smart manufacturing, and sustainable energy systems. His research bridges theoretical foundations with real-world applications through collaborative projects with industry partners. Analysis of his recent publications reveals a strong focus on explainability in sequential decision-making, with increasing integration of large language models to enhance traditional planning algorithms. His work spans theoretical foundations of Monte Carlo Tree Search, programmatic policy generation, multi-agent reinforcement learning, and practical applications of these techniques. A notable trend is the growing emphasis on human-AI collaboration, where AI systems must not only perform well but also effectively communicate their reasoning to human users. Dr. Baier actively collaborates with researchers across multiple institutions, including CWI Amsterdam where he maintains an affiliation, and has participated in significant interdisciplinary efforts such as the Dagstuhl Seminar on Explainable AI for Sequential Decision Making. His research group at TU/e works closely with industry partners to translate fundamental research into practical applications. He is affiliated with EAISI (Eindhoven Artificial Intelligence Systems Institute) and contributes to the Decision Making with Artificial Intelligence educational program at TU/e. His laboratory work focuses on developing benchmark environments and frameworks that enable rigorous evaluation of decision-making algorithms, with recent contributions including MOMAland for multi-objective multi-agent reinforcement learning.

Jasper GoselingView profile

Associate Professor

• Differential Privacy
• Network Coding
• Optimization Problem
• +4 more

Jasper Goseling is an Associate Professor at the Digital Society Institute and affiliated with the Mathematics of Operations Research department. His research spans differential privacy, network coding, optimization, and wireless systems, often bridging theoretical and applied domains. Key research areas: Differential Privacy, Network Coding, Optimization, Wireless Sensor Networks, Machine Learning His recent work focuses on robust optimization techniques for local differential privacy, addressing trade-offs between data utility and privacy preservation. Earlier contributions include studies on energy-efficient data collection in sensor networks, caching strategies in wireless environments, and entropy-based analysis of hydrothermal systems. Article trends reveal a strong emphasis on privacy-preserving algorithms (2022-2024) and historical expertise in network coding, queueing theory, and thermodynamic entropy. His research integrates mathematical rigor with practical applications in wireless communication and data management. Activities include organizing the 45th Symposium on Information Theory and Signal Processing (2025) and leadership roles in the IEEE Benelux Chapter on Information Theory (Chair, 2017; Member, 2012-2017). He also contributed to the 2015 European School of Information Theory.

• Geotechnical Engineering
• Soil Mechanics
• Material Point Method (MPM)
• +7 more

Michael Hicks is a Professor at Delft University of Technology (TU Delft) in the Civil Engineering & Geosciences school, specializing in Geo-engineering . His research focuses on geotechnical risk assessment, soil variability, and advanced numerical methods like the Material Point Method (MPM) to model slope failures, earthquake simulations, and soil-structure interactions. Editorial board member for Géotechnique , Georisk , and Computers and Geotechnics (2019) Keynote speaker at workshops on slope failure modeling (2018) Active in public engagement about flood risk management (2017–2018) His work addresses challenges in soil heterogeneity, dynamic boundary conditions, and reliability-based design for infrastructure. Notable contributions include developing probabilistic MPM frameworks and machine learning tools for CPT data interpretation, with applications in earthquake resilience and radioactive waste repository safety. Recent publications highlight innovations in 3D slope stability analysis, nonlocal soil deformation modeling, and thermomechanical interface behavior under cyclic loading. Collaborations span academia and industry, focusing on improving numerical accuracy and understanding failure mechanisms in geotechnical systems.

• Financial Mathematics
• Financial Engineering
• Computational Finance
• +5 more

Dr. ir. Lech Grzelak is an Associate Professor at the Mathematical Institute within Utrecht University's Faculty of Science. His research focuses on Financial Mathematics, Computational Finance, and Quantitative Finance, with a strong emphasis on Stochastic Differential Equations (SDEs), Volatility Modeling, and Hybrid Derivatives. University : Utrecht University Academic Rank : Associate Professor Department : Mathematical Institute Grzelak's work spans Stochastic Volatility Models , Local Volatility Models , and Valuation Adjustments (xVA) . He has developed innovative methods like the Seven-League Scheme for large time-step Monte Carlo simulations and Stochastic Collocation techniques for efficient sampling. Recent research trends include: Integration of Deep Learning with Monte Carlo for SDE simulation (GANs-based approaches) Hybrid models combining Stochastic Volatility and Stochastic Interest Rates Collateral Choice Options and Wrong-Way Risk modeling Applications in VIX Options , Basket Options , and Commodity Derivatives He is an associate editor for the Journal of Computational Finance and Journal of Applied Mathematics and Computation . Grzelak also provides free educational content through his ComputationsInFinance YouTube channel and offers a Computational Finance Course online.

Bernd RiegerView profile

Professor

• Computational microscopy
• Optical nanoscopy
• Image processing
• +3 more

Bernd Rieger (born 1973) is a Professor at the Faculty of Applied Sciences of Delft University of Technology (TU Delft), Netherlands. He leads the Computational Imaging group within the Department of Imaging Physics (ImPhys). Appointed as Antoni van Leeuwenhoek full professor in 2017, he has established himself as a leading researcher in advanced microscopy techniques. His educational background includes an M.Sc. in physics from Technische Universität München (1999) and a Ph.D. in image processing and analysis from Delft University of Technology (2004). After completing his doctoral studies, he conducted postdoctoral research at the Max Planck Institute for Biophysical Chemistry in Göttingen, Germany. Rieger's research focuses on Computational Microscopy , which combines imaging physics and image processing specifically for light and electron microscopy applications in life sciences at the biomolecular level. His work spans optical nanoscopy, image processing algorithms, and electron microscopy techniques, with particular emphasis on improving resolution and developing novel imaging methodologies. The research has significant implications for understanding cellular structures and molecular interactions. Analysis of his recent publications reveals a strong focus on improving microscopy resolution techniques, developing image processing algorithms for microscopy data, and advancing super-resolution imaging methods. His work combines theoretical foundations with practical applications in biological imaging, particularly in the areas of structured illumination microscopy, DNA-PAINT, and Fourier analysis techniques for resolution assessment. ERC Consolidator Grant (2015) to investigate ways to further improve the resolution towards 1 nm in the field of optical nanoscopy Professor Rieger has successfully secured significant research funding, including the prestigious ERC Consolidator Grant. His research group collaborates extensively with other institutions and researchers across Europe. The group maintains strong connections with industry partners, particularly in the microscopy equipment sector, building on Rieger's earlier experience at FEI Electron Optics. The Rieger group operates advanced microscopy facilities at TU Delft, focusing on computational approaches to enhance imaging capabilities. The lab integrates physics-based modeling with sophisticated image processing techniques to push the boundaries of what's possible in optical and electron microscopy. Current research directions include 3D structured illumination microscopy, single-molecule localization techniques, and novel approaches to quantitative image analysis in biological contexts.

Sjoerd StallingaView profile

Professor

• Computational Imaging
• Super-Resolution Microscopy
• Digital Pathology
• +4 more

Sjoerd Stallinga is a full Professor in the Department of Imaging Physics within the Faculty of Applied Sciences at Delft University of Technology (TU Delft). He joined TU Delft in 2009 as an associate professor and was promoted to full professor in 2018. His academic journey began at the University of Nijmegen where he obtained both his graduate degree (1993) and PhD (1995) in theoretical liquid crystal physics. Stallinga's research focuses on computational optical imaging systems, with particular emphasis on biomedical applications. His primary research interests include computational imaging, super-resolution microscopy, digital pathology, optical nanoscopy, and general microscopy techniques. His work bridges theoretical physics, optical engineering, and biomedical applications, with a strong focus on developing novel imaging technologies for biological and medical research. His recent publications demonstrate a consistent focus on advancing imaging techniques, particularly in structured illumination microscopy, deconvolution algorithms, single-molecule localization microscopy, and image quality assessment. These works collectively contribute to pushing the boundaries of optical resolution and image processing in biological imaging. ERC Advanced Grant (2022) for making super detailed 3D images of proteins in living cells Zwaartekracht funding for living cells consortium (2022) Professor Stallinga has secured significant research funding including an ERC Advanced Grant and Zwaartekracht funding for a living cells consortium. His research group has developed innovative approaches in computational imaging and microscopy, with applications in biomedical research. The lab has produced numerous high-impact publications and has made significant contributions to the field of super-resolution microscopy and digital pathology. The ImPhys/Stallinga group at TU Delft focuses on the analysis, design, and realization of computational optical imaging systems. The team collaborates extensively with other researchers in the Netherlands and internationally, as evidenced by their numerous co-authored publications. Their work has practical applications in biomedical imaging, particularly in optical nanoscopy and digital pathology.

• Philosophy of Artificial Intelligence
• Cognitive Science
• Neuroscience
• +3 more

Carlos Zednik is an Assistant Professor for Philosophy of Artificial Intelligence at Eindhoven University of Technology , affiliated with the Industrial Engineering and Innovation Sciences department. He leads the Eindhoven Center for Philosophy of AI and participates in the alignAI (ERC) and ROBUST AI (NWO) consortia. His work bridges philosophy with AI and neuroscience, focusing on explainable AI (XAI), mechanistic explanation, and cognitive modeling. Education: BSc in Computer Science and Philosophy, Cornell University MSc in Philosophy of Mind, University of Warwick PhD in Cognitive Science, Indiana University Bloomington Zednik’s research investigates philosophical questions about biological and artificial intelligence, emphasizing: Methodological principles in cognitive psychology and neuroscience Norms and best practices for XAI in machine learning Knowledge representation in transformer models and large neural networks His recent publications explore the integration of cognitive models into XAI, the role of Bayesian reverse-engineering in cognitive science, and the mechanistic explanation of network neuroscience. Zednik also contributes to international standardization efforts through ISO/IEC TS 6254 and DIN SPEC 92001 . Scientific Awards include fellowships from: DAAD Alexander-von-Humboldt Foundation StandICT Fellowship Zednik supervises PhD students Zeynep Kabadere , Michela Ghezzi , Céline Budding , Miriam Gorr , and Hannes Boelsen , while mentoring postdocs Manuel Barbosa de Oliveira and Philippe Verreault-Julien . His teaching spans philosophy of AI, ethics of machine learning, and decision theory, with innovation projects on generative AI in higher education.

• Quantum Physics
• Condensed Matter Physics
• Theoretical Physics
• +3 more

Prof. Kareljan Schoutens is a Professor at the University of Amsterdam, affiliated with the Institute for Theoretical Physics (ITF) within the Faculty of Science. His research focuses on quantum many-body systems, supersymmetry, topological phases of matter, and quantum computing. He explores topics such as quantum simulation, quantum gate implementations in trapped ions, and non-equilibrium dynamics in strongly correlated systems. His work bridges theoretical physics with experimental realizations, particularly in condensed matter and atomic physics contexts. He oversees research projects and supervises students in these areas. Key research interests include quantum many-body scars, fermionic systems with global symmetries, lattice models with supersymmetry, and the application of quantum information techniques to understand complex systems. His contributions span theoretical frameworks for quantum algorithms, topological protection mechanisms, and the interplay between symmetry and critical phenomena. Publications highlight advancements in quantum gate design for trapped ions, analysis of many-body systems in ladder geometries, and studies of topological phases in coupled fermionic chains. His work often emphasizes exact solutions and numerical methods to uncover novel quantum phenomena. Prof. Schoutens collaborates on grants and supervision in theoretical physics, contributing to the National Quantum Technology Agenda in the Netherlands. He is part of interdisciplinary efforts at the ITF, addressing challenges in quantum information science and condensed matter theory.

• Mathematical Finance
• Financial Risk Management
• Quantitative Finance
• +3 more

Dilip B. Madan is the Robert H. Smith School of Business Professor at the University of Maryland College Park. He holds PhDs in Economics (1971) and Mathematics (1975) from the same institution. His primary research focuses on Mathematical Finance, stochastic processes, and risk management with applications to financial derivatives and systemic risk. Education: PhD in Economics, University of Maryland, 1971 PhD in Mathematics, University of Maryland, 1975 Research Interests: Professor Madan’s work addresses critical financial challenges including valuation of derivatives, risk allocation mechanisms, and regulatory capital requirements. He pioneered the use of Lévy processes in financial modeling and contributed foundational concepts in conic finance. His research bridges theoretical rigor with practical applications in risk management and market design. Key Themes in Articles: His publications emphasize the integration of stochastic processes (particularly Lévy processes) into financial modeling frameworks, exploring topics such as capital adequacy, socially acceptable risk metrics, and dynamic hedging strategies under non-Gaussian market conditions. Recent work introduces conic finance principles to address counterparty risk and systemic stability concerns. Professional Roles: Consultant: Morgan Stanley, Caspian Capital LLC, FDIC Editorial Roles: Co-Editor of Mathematical Finance , Associate Editor of Quantitative Finance Leadership: Founding Member & Past President of the Bachelier Finance Society

• Electoral Systems
• Political Science
• Economic Inequality
• +3 more

Henk van der Kolk is an Associate Professor specializing in Electoral Systems , Political Science , and Democracy Research . His work focuses on electoral reform , voter behavior , and political inequality , with a strong emphasis on the Netherlands and comparative European contexts. Key research themes: Electoral systems, proportional representation, voter turnout, family policy impacts, and gender-based economic inequality Notable contributions: Analysis of ballot design , referendum dynamics , and institutional reforms in local and national governance His recent publications (2024) explore election timing, ballot invalidation, and electoral system redesign, reflecting a focus on democratic innovation and institutional engineering . Earlier works (2017-2019) investigate gendered economic disparities and longitudinal trends in political engagement . He also contributes to major datasets like the Dutch Parliamentary Election Study (2017), advancing empirical research in electoral politics. While no specific awards or student supervision details are listed, his extensive publication record (over 150 works) and cross-national collaborations (e.g., Comparative Study of Electoral Systems) underscore his prominence in democracy research and political methodology .

Boudewijn van DongenView profile

Professor

• Process Mining
• Conformance Checking
• Business Process Management
• +3 more

Dr. Boudewijn van Dongen is a Full Professor at Eindhoven University of Technology's Department of Mathematics and Computer Science, chairing the Process Analytics group. His research focuses on conformance checking and process mining , particularly through alignment-based techniques. Develops ProM and CPN Tools frameworks Collaborates with Philips Research and Vanderlande Leads IEEE Task Force on Process Mining Research Interests : Specializes in aligning observed data with process models, addressing multi-case dependencies , privacy-aware mining , and stream processing . Project Highlights : • Strategic partnership with Philips on health data science • Logistics optimization with Vanderlande Industries • Foundational work in alignment theory and behavioral diagnostics

Wil P.A.J. MichielsView profile

Professor

• Attack Analysis
• Binary Instrumentation
• Reverse Engineering
• +5 more

Wil P.A.J. Michiels serves as a Full Professor in the Mathematics and Computer Science faculty at Eindhoven University of Technology (TU/e), specializing in cryptography and computer security. His research focuses on white-box cryptography, reverse engineering, and attack analysis within secure systems. His research interests span Attack Analysis , Binary Instrumentation , Reverse Engineering , Execution Trace analysis, and Cryptographic Primitive development. His work bridges theoretical cryptography with practical security implementations, particularly in protecting cryptographic algorithms against advanced attacks. Michiels' publication trends reveal deep specialization in white-box cryptography security models, with significant contributions to provable security frameworks and attack mitigation strategies. His research consistently addresses real-world security challenges in cryptographic implementations. Award highlights include: US Patent for Protecting the input/output of modular encoded white-box RSA US Patent for Balanced encoding of intermediate values within a white-box implementation He actively supervises academic work with 15 supervised projects documented and leads the active TKI-HTSM/22.0547/TKI2212P11 RaidarAI project (2021-2027) focused on AI security applications. His research integrates theoretical cryptography with industrial security applications through collaborations with entities like NXP.