Find Academic Supervisors

Prof. Florian Wellmann is a University Professor at RWTH Aachen University's Chair of Numerical Geosciences, Geothermal Energy and Reservoir Geophysics within the Faculty of Georesources and Materials Engineering. His research focuses on integrating machine learning with geoscience applications, particularly in geothermal energy, structural modeling, and uncertainty quantification. He leads the CG³ research group, developing open-source tools like GemPy and GemGIS for 3D geological modeling. Notably, he received a KI-Campus fellowship for advancing AI in geoscience education. His work includes projects such as the Horizon Europe GeoHEAT initiative, exploring geothermal systems and repurposing idle wells for energy. Education details are not explicitly provided, but his academic roles indicate expertise in numerical geosciences and geothermal engineering. Research interests span physics-based machine learning, subsurface characterization, and probabilistic modeling. His fellowship highlights contributions to digital education, blending AI with geological curricula. Recent publications emphasize sensitivity analysis, fault modeling, and geothermal reservoir optimization. Prof. Wellmann's awards include the KI-Campus fellowship (2021). His grants and advising efforts are reflected in collaborative projects like GeoHEAT and software development. Labs/teams include the CG³ group at RWTH Aachen, equipped with advanced geophysical instruments for field and lab analysis.

• Geothermal Energy
• Structural Geology
• Geophysical Modeling
• +3 more

Professor Tony Jebara is a faculty member in the Department of Computer Science at Columbia University, where he chairs the Center on Foundations of Data Science and directs the Columbia Machine Learning Laboratory. His research focuses on machine learning with applications in vision, graphs, and spatio-temporal data. He holds a PhD from MIT (2002) and has advised startups including Sense Networks, Evidation Health, and Agolo. Notable awards include the NSF Career Award (2004), Best Paper at ICML 2009, and recognition as one of Esquire's Best and Brightest (2008). His work has been featured in major media outlets. Jebara's academic contributions span over 100 peer-reviewed papers and a textbook on machine learning. He served as General Chair for ICML 2017 and Program Chair for ICML 2014. His research explores generative and discriminative models, Bayesian inference, and optimization techniques. Current projects include neural ensemble analysis in neuroscience and robust learning algorithms for environmental modeling. Recent publications emphasize scalable methods for collaborative filtering, survival analysis in online experiments, and graphical model applications in neuroscience. His work bridges theoretical advancements with practical systems, including contributions to privacy-preserving algorithms and recommendation systems.

• Machine Learning
• Computer Vision
• Graph Theory
• +3 more

Hervé Delingette is a Research Director at Inria, a leading national research institute in France, where he is a key member of the Asclepios research team. He also holds a Chair at the 3IA Côte d'Azur Institute and leads the CardioSense3D Large Initiative Action, focusing on advanced modeling of the heart's electro-mechanical behavior. His work bridges artificial intelligence, medical imaging, and computational biology. His research interests are centered on computational medicine and include: Image Segmentation Surface Regularization and Simplex Mesh Surgery Simulation Cardiac and Brain Modeling Joint biological and imaging biomarkers in oncology Unsupervised deep learning for medical data Uncertainty quantification and sparse Bayesian feature selection His recent work emphasizes integrating imaging and biological data—particularly in lung cancer—to improve diagnosis and treatment planning by addressing confounding factors and leveraging AI. Although no specific publications or awards are listed in the source, his leadership in major research initiatives underscores his significant contributions to AI in medicine. He mentors researchers within his team and leads interdisciplinary projects funded through Inria and the 3IA Institute. He is based at Inria Sophia Antipolis and actively contributes to France's national AI for health strategy.

• Computational Medicine
• Medical Image Analysis
• Cardiac Modeling
• +12 more

Zhuo Chen is an Adjunct Lecturer in the Department of Civil & Environmental Engineering at Monash University. His research focuses on sustainable urban planning, transportation engineering, and materials science, particularly in additive manufacturing and microstructural analysis. He has collaborated on projects addressing bike-friendly infrastructure, urban heat island effects, EV charging etiquette, and the development of advanced materials through novel processing techniques. Key research interests include integrating deep learning for urban infrastructure analysis, leveraging social media data for mobility studies, and optimizing additive manufacturing processes to enhance material properties. His work contributes to the UN Sustainable Development Goals, particularly in sustainable cities and communities (SDG 11) and climate action (SDG 13). Recent studies highlight trends in both transportation innovation (e.g., protected cycle lanes, EV infrastructure) and materials science (e.g., laser powder bed fusion, alloy development). His interdisciplinary approach bridges urban policy and advanced manufacturing, with applications in smart cities and nuclear materials. Zhuo Chen has been actively engaged with the Monash Suzhou Research Institute through patent collaborations, focusing on innovative manufacturing solutions. His work emphasizes empirical validation and data-driven methodologies to address real-world challenges in urban and materials engineering.

• Sustainable Urban Planning
• Transportation Engineering
• Additive Manufacturing
• +3 more

Andreas Fender is a researcher at the Visualization Institute of the University of Stuttgart (VISUS), affiliated with the Schmalstieg Working Group. He has held postdoctoral positions at ETH Zurich (Switzerland) and the University of Sussex (England), following his PhD at Aarhus University (Denmark) with an internship at Microsoft Research (USA). His research focuses on Human-Computer Interaction, particularly in Augmented and Virtual Reality (AR/VR) and camera networks. He develops novel input methods for productivity and artistic expression in Mixed Reality environments, creating hybrid physical-digital systems like OptiBasePen, PressurePick, InfinitePaint, and DeltaPen. Recent work includes contributions to Mixed Reality input methods (UIST 2024, CHI 2022) and collaborative systems (Asynchronous Reality). Projects like GuitarPie (UIST 2025) and OptiBasePen (UIST 2024) demonstrate his focus on mobile interaction and ergonomic design. Scientific accolades include the Best paper award at CHI 2022 Best application paper award at ISS 2019 . At VISUS, he collaborates with Dieter Schmalstieg and leads hiring for PhD students and PostDocs exploring physical-digital workflows, artistic tools, and critical AI engagement. His work integrates machine learning, hardware prototyping, and spatial user interfaces to redefine future workplaces.

• Human-Computer Interaction
• Augmented Reality
• Virtual Reality
• +6 more

Audrey Repetti is an Associate Professor in the Department of Actuarial Mathematics and Statistics within the School of Mathematical and Computer Sciences at Heriot-Watt University in Edinburgh, UK. She also holds a dual affiliation with the Institute of Sensors, Signals, and Systems in the School of Engineering and Physical Sciences, and is part of the Maxwell Institute for Mathematical Sciences - Edinburgh. Her research spans mathematical imaging, optimization, and computational methods with applications across astronomy, medical imaging, and optical engineering. Dr. Repetti's research focuses on developing advanced mathematical frameworks for solving imaging inverse problems. Her work centers on optimization algorithms, Bayesian uncertainty quantification, and the integration of machine learning with traditional mathematical approaches. She has made significant contributions to radio interferometric imaging, computational optical imaging with photonic lanterns, and uncertainty quantification in medical imaging. Her research bridges theoretical mathematics with practical applications in astronomy, healthcare, and engineering. Analysis of her recent publications reveals a clear trajectory toward integrating traditional mathematical imaging approaches with modern machine learning techniques. Her work increasingly focuses on 'hybrid' methodologies that combine data-driven models with optimization frameworks. Key themes include plug-and-play algorithms, uncertainty quantification in imaging, and the development of efficient computational methods for high-dimensional inverse problems. Her research demonstrates strong interdisciplinary connections between mathematics, signal processing, astronomy, and medical imaging. Dr. Repetti is actively involved in academic service, including co-organizing the 2026 ICMS Workshop on Imaging inverse problems and generating models. She has received research funding supporting her work in computational imaging and inverse problems, though specific grant details aren't listed in the provided materials. Her teaching portfolio includes advanced courses in scalable inference, deep learning, and statistics for sciences. She leads several research projects with associated software toolboxes including BUQO (Bayesian Uncertainty Quantification by Optimization), SARA-COIL (Compressive optical imaging with a photonic lantern), and CALIM (Self direction-dependent effect calibration and imaging in radio-interferometry). These projects demonstrate her commitment to developing practical computational tools that advance both theoretical understanding and real-world applications in imaging science.

• Image processing
• Inverse problems
• Radio interferometric imaging
• +7 more

Laurent Charlin is an Associate Professor at HEC Montréal and holds an adjunct appointment in Computer Science at Université de Montréal. His research focuses on machine learning for decision-making with applications in recommender systems, reinforcement learning, and optimization.

• Machine Learning
• Artificial Intelligence
• Recommender Systems
• +6 more

Andrea Tigrini serves as a Researcher in the Department of Information Engineering at Marche Polytechnic University's School of Engineering in Ancona, Italy. His scientific sector is Bioengineering (IBIO-01/A), with research spanning biomedical signal processing and human motion analysis. Dr. Tigrini's research interests focus on the intersection of biomedical engineering and machine learning, particularly in developing innovative approaches for human motion analysis through electromyography (EMG) and inertial sensing. His work emphasizes creating minimal-sensor solutions for practical applications in rehabilitation technologies, gait analysis, and assistive devices. He investigates neuromuscular control mechanisms during various activities including walking, balance maintenance, and hand gestures. Analysis of his recent publications (2023-2025) reveals a strong trend toward developing accessible diagnostic and assistive technologies using machine learning approaches. His research consistently addresses real-world challenges in diabetic neuropathy detection, prosthetic control, and rehabilitation monitoring, with particular emphasis on creating solutions that require minimal sensor setups to enhance practicality and adoption in clinical settings. His work demonstrates significant contributions to understanding the relationship between neuromuscular signals and movement patterns, with applications spanning rehabilitation engineering, human-computer interaction, and clinical diagnostics. The interdisciplinary nature of his research bridges engineering principles with physiological understanding to create practical healthcare solutions.

• Biomedical Engineering
• Human Motion Analysis
• Electromyography
• +4 more

Adrian Bors is a Senior Lecturer in the Department of Computer Science at the University of York. His research focuses on computer vision, computational intelligence, image processing, and pattern recognition, with expertise in neural networks and digital watermarking. He received his MSc from the Polytechnic University of Bucharest (1992) and a PhD from Aristotle University of Thessaloniki (1999). His career includes research roles at Tampere University of Technology, Aristotle University of Thessaloniki, and the University of York, where he has been a Lecturer since 2000 and Senior Lecturer since 2001. His recent publications emphasize task-free continual learning, generative modeling, and steganalysis. Key trends include dynamic neural architectures, vision transformers, and applications of optimal transport theory in lifelong learning systems. He is an IEEE Senior Member and contributes to editorial roles in IEEE Transactions.

• Computer vision
• Computational intelligence
• Image processing
• +4 more

Dr. Frank Soboczenski is a Lecturer in the Department of Computer Science at the University of York, with an affiliate scientist position at King's College London supported by the NVIDIA GPU Grant Program. His research spans multiple domains including healthcare, space research, and quantum machine learning applications. He serves as a STEM scientist for NASA's and NOAA's GLOBE program and is actively involved in various NASA initiatives including the Frontier Development Lab. Dr. Soboczenski's primary research interests include Transformers and Large Language Models, Machine Learning with focus on Uncertainty Quantification and Explainability, and advanced applications of Quantum Machine Learning in Healthcare/Biomedicine and Space Research domains. His work on the RobotReviewer project applies Deep Learning and Natural Language Processing to healthcare. Previously, he has worked in Human-Computer Interaction, Cyber-Security, and Real-Time Systems in cooperation with organizations including the German Police Force, GCHQ, Rapita Systems, INRIA, Barcelona Supercomputing Center, and Airbus. His recent publications demonstrate a strong focus on applying machine learning techniques to healthcare informatics and space research, with particular emphasis on systematic reviews, clinical decision support, atmospheric retrieval for exoplanets, and medical data analysis. His work bridges the gap between theoretical AI advancements and practical applications in critical domains. NASA TechLeap Prize - Quantum Machine Learning NASA/NOAA/U.S. Department of State Outstanding Efforts to Mentor and Support Students (2019-present) NASA Frontier Development Lab AI Research Award of Merit Data Samaritan Award Steely Eyed Operator Award NASA Kennedy Space Center OsirisREx launch invitation SpaceApps 3M Thesis Competition UK National Winner (2013) Deggendorf Institute of Technology Robotics Challenge Award Dr. Soboczenski actively mentors students, as evidenced by his NASA/NOAA award for mentoring. His research is supported by the NVIDIA Corporation through the GPU Grant Program. He serves on multiple program committees including NeurIPS (2019-present), AAAI (2019-present), and various specialized workshops at major AI conferences. He is also involved in organizing NASA Space Apps challenges and serves on the NASA GeneLab Analysis Working Group on AI/ML. As an active member of the academic community, Dr. Soboczenski participates in numerous professional organizations including the NASA Nancy Grace Roman Spacecraft Science Working Group, NASA Technosignatures research group, IBM Quantum Researchers Program, PolarAI Research Group of the ACM, Huggingface BigScience Team, International Astronomical Union, and several others focused on AI and space research.

• Transformers
• Large Language Models
• Machine Learning
• +11 more

Selin Aslan serves as an Assistant Professor in the Department of Mathematics at Koç University, Istanbul, Turkey, where she conducts research at the intersection of computational mathematics and imaging science. Her academic appointments and research activities are centered within the university's mathematics department, contributing to both undergraduate and graduate education in mathematical sciences. Her educational qualifications include: PhD in Mathematics from Virginia Polytechnic Institute and State University (2018) Master's in Mathematics from Rochester Institute of Technology (2013) B.A. in Mathematics from Ege University (2010) Dr. Aslan's research program focuses on developing advanced computational methods for solving inverse problems in imaging, with particular expertise in phase retrieval, tomographic reconstruction, and ptychography. Her work bridges theoretical mathematics with practical applications in medical imaging, microscopy, and materials science, emphasizing algorithmic innovation and computational efficiency. She integrates techniques from deep learning, optimization theory, and high-performance computing to address challenges in image reconstruction under physical constraints. Analysis of her publication record reveals a consistent trajectory toward solving complex imaging problems through hybrid approaches that combine physics-based models with data-driven techniques. Her recent work demonstrates increasing emphasis on scalability for large datasets, robustness in photon-limited scenarios, and real-time processing capabilities, with applications spanning biomedical imaging to advanced microscopy. No scientific awards were documented in the available sources. Information regarding student advising and research grant activities was not specified in the provided materials, though her publication record suggests active research collaboration. Her computational focus implies engagement with high-performance computing resources for large-scale image reconstruction tasks. While specific laboratory infrastructure details were unavailable, her research on multi-GPU implementations and distributed computing indicates utilization of advanced computational facilities for handling large-scale imaging datasets.

• Applied Mathematics
• Computational Mathematics
• Imaging Science
• +2 more

Ardeshir Ebtehaj is an Associate Professor at the University of Minnesota's College of Science & Engineering, Department of Civil, Environmental and Geo-Engineering. He leads the Hydrologic Sciences and Remote Sensing (HydSens) Laboratory at the Saint Anthony Falls Laboratory (SAFL) and serves as Editor of the Journal of Hydrometeorology. His research integrates physical models with data science to address sustainable water, food, and energy systems. Education: Postdoctoral Research, Georgia Institute of Technology Ph.D., University of Minnesota, Water Resources and Hydrology M.Sc., University of Minnesota, Mathematics M.Sc., Iran University of Science and Technology, Environmental Engineering M.Sc., Iran University of Science and Technology, Structural Engineering B.Sc., Iran University of Science and Technology, Civil Engineering Research Interests: Electromagnetic hydrology, satellite hydrometeorology, microwave remote sensing, inverse problems, land-atmosphere interactions, climate intelligence, and machine learning applications for water and environmental monitoring. Awards & Grants: Recent funding from NASA (Arctic ecohydrology modeling, SMAP program) and USACE (Harmful Algal Blooms detection). Collaborations: HydSens team at SAFL, NASA Goddard Space Flight Center, University of Alaska.

• Hydrology
• Remote Sensing
• Environmental Science
• +5 more

Martina Pastorino is a Researcher in the Department of Naval, Electrical, Electronic, and Telecommunications Engineering (DITEN) at the University of Genoa. Her work focuses on integrating machine learning with probabilistic graphical models for advanced remote sensing image analysis , particularly in multiresolution classification using satellite and UAV data. She teaches courses on Machine Learning for Pattern Recognition and Remote Sensing in master’s programs related to Internet and Multimedia Engineering and Energy Engineering . Research Interests : Remote Sensing, Machine Learning, Image Segmentation, Data Fusion, Hyperspectral Imaging, UAV Applications. Key Techniques : CNN-MRF Hybrids, CRFNet, Probabilistic Graphical Modeling, Multiresolution Analysis. Her recent publications explore applications in wildfire mapping , urban land-use analysis , and hyperspectral-panchromatic fusion , with a focus on improving semantic segmentation accuracy through hybrid deep learning frameworks. She is available for office hours on request via email at martina.pastorino@unige.it .

• Remote Sensing
• Machine Learning
• Image Processing
• +4 more

Dr. Jun Liu serves as an Associate Professor in the Department of Civil, Construction and Environmental Engineering within the College of Engineering at the University of Alabama. He directs the NextGen Transportation Lab and holds editorial positions including Managing Editor for the Journal of Intelligent Transportation Systems. His affiliations include the Center for Sustainable Infrastructure and Center for Transportation Operations, Planning and Safety. Ph.D. in Civil Engineering, University of Tennessee (2015) M.S. in Statistics, University of Tennessee (2015) M.S. in Transportation Planning & Management, Huazhong University of Science & Technology (2011) B.S. in Transportation Engineering, Huazhong University of Science & Technology (2008) Dr. Liu's research spans transportation safety, connected/automated vehicles, and sustainable mobility systems. His work integrates machine learning with geospatial analysis to address responder safety, travel behavior, and urban planning challenges. Current projects focus on generative AI applications, EV infrastructure, and rural transportation equity. His methodology combines agent-based simulation, spatial modeling, and behavioral pathway analysis to develop practical transportation solutions. Publication trends reveal strong emphasis on machine learning applications in transportation safety (32% of recent works), with significant contributions to connected vehicle systems (24%) and sustainable mobility solutions (18%). His research demonstrates consistent integration of spatial analysis techniques across 78% of publications, with increasing focus on generative AI applications since 2023. Recent work shows growing international collaboration, particularly with Chinese institutions on robotaxi deployment. Inaugural Editorial Board Member, Transportation Research Record 2018 Small Grants Program Award, University of Alabama Distinguished Scientific Paper Award, ITS World Congress Best Reviewer, Journal of Traffic and Transportation Engineering Dr. Liu has secured over $21 million in research funding since 2018, including an NIH/CDC R01 award as lead PI. His 30 projects include 17 as Principal Investigator from NSF, NIH/CDC, US DOT, and state agencies. He mentors numerous graduate students, with recent publications featuring trainees as first authors. Current initiatives include a $2 million CDC/NIOSH project on first responder safety and $16.8 million smart transportation network development in West Alabama. His NextGen Transportation Lab focuses on integrating AI with transportation systems while exploring creative applications through dance and choreography.

• Transportation Safety
• Responder Safety
• Intelligent Transportation Systems
• +7 more

Prof. Dr. Yarema Okhrin serves as Full Professor at the Department of Statistics and Data Science within the Faculty of Economics at the University of Augsburg. He leads the Chair of Statistics and Data Science, which is part of the Business Analytics & Operations and Finance, Accounting, Controlling & Taxation clusters. His research group includes Dr. Sebastian Heiden, Dr. Rui Ren, and several research assistants working on advanced statistical methods and their applications in business and economics. Professor Okhrin's research spans mathematical and statistical models for data-driven problems in business and economics, with particular expertise in statistics, data science, and machine learning. His work focuses on developing methodologies for time series analysis, portfolio optimization, risk management, and statistical process control. Recent research has expanded into high-dimensional statistics, image analysis, and network monitoring applications. Analysis of his recent publications (2023-2025) reveals a strong trend toward interdisciplinary applications of statistical methods, particularly in finance and process monitoring. His work demonstrates increasing integration of machine learning techniques with traditional statistical approaches, especially in portfolio optimization and risk assessment. A notable pattern is the development of specialized statistical methods for high-dimensional data analysis across multiple domains. Professor Okhrin supervises bachelor's and master's theses at the Department of Statistics, with research topics including data mining, time series modeling, forecasting methods, regression analysis, and statistical data analysis. His department offers thesis opportunities in specialized areas such as asymmetric dependencies in financial markets, forecasting, investor sentiment analysis, medical statistics, volatility modeling, multivariate distributions, sustainable investing, and portfolio optimization. The Chair of Statistics maintains active research collaborations and offers academic consulting on statistical issues and data analysis. The department hosts regular research seminars to facilitate exchange of ongoing research projects and maintains connections with industry partners for practical applications of statistical methods.

• Statistics
• Data Science
• Machine Learning
• +7 more