Find Academic Supervisors

Gordana ĐukanovićView profile

Associate Professor

• Geometry of architectural form
• Descriptive geometry
• Relativistic geometry
• +4 more

Gordana Đukanović is an Associate Professor at the Faculty of Forestry, University of Belgrade, where she has been employed since October 1, 1994. She currently teaches courses in geometry, engineering graphics, and related subjects across multiple academic programs including Basic Academic Studies, Master's programs, and Vocational Studies. Education: Graduated from the "Vuk Karadžić" High School (mathematics department - programmer) in Loznica Graduated from the Faculty of Civil Engineering in Belgrade (Construction department) on March 7, 1988 Defended her master's thesis from the Faculty of Architecture in Belgrade on December 26, 2000 Defended her doctoral dissertation from the Faculty of Architecture, University of Belgrade on November 2, 2012 Professor Đukanović specializes in the geometry of architectural form with research focusing on descriptive geometry, relativistic geometry, engineering graphics, and photogrammetry. Her work bridges architectural theory with practical applications in forest engineering and building design. She has published 49 papers including more than 5 peer-reviewed scientific papers in journals, 35 papers presented at congresses and symposia, one practical guide, and numerous studies and projects for wood processing companies. Her recent publications demonstrate a strong interdisciplinary approach connecting geometry with environmental science, architecture, and engineering. The research spans from theoretical mathematical explorations to practical applications in air pollution analysis, flood management, structural integrity assessment, and renewable energy systems design. Scientific Awards and Recognition: University Scholarship as one of the three students with the best grade point average during the first two years of university Certified court expert in the field of building valuation Professor Đukanović serves as a member of the Serbian Society for Geometry and Graphics (SUGIG) and the International Society for Geometry and Graphics (ISGG). She has passed the professional exam in civil engineering at the Association of Engineers and Technicians of Serbia. Her teaching responsibilities include courses in descriptive geometry with engineering graphics for Ecological Engineering in Land and Water Resources Protection, Furniture and Wood Products Construction, and Technology of Wood House Production.

Alain PaganiView profile

Researcher

• Computer Vision
• Artificial Intelligence
• Image Understanding
• +6 more

Alain Pagani is a Principal Researcher and Deputy Director of the Augmented Vision department at the German Research Center for Artificial Intelligence (DFKI) . He leads a team of 10 PhD students and researchers, focusing on Augmented Reality, Computer Vision, and Machine Learning. Research Interests include 3D Computer Vision, Image-based Scene Reconstruction, Object Detection and Tracking, and Extended Reality (AR/VR) applications. His work spans both industrial and academic projects, such as the EU initiatives dAIEDGE , CORTEX² , and FLUENTLY . Scientific Awards include a Google Research Award, Best Paper Award (INI-GraphicsNet 2007 Honorable Mentions), and Best Paper Award (INI-GraphicsNet 2008 Honorable Mentions). Projects like dAIEDGE (AI at the Edge) and CORTEX² (Collaborative XR) highlight his leadership in distributed AI and real-time extended reality systems. He has also coordinated EU projects such as LARA (Outdoor AR using Galileo) and Eyes of Things (Low-power Computer Vision).

Heather LynchView profile

Professor

• Remote Sensing
• Bayesian Inference
• Time Series Modelling
• +7 more

Heather Lynch is the IACS Endowed Professor of Ecology & Evolution at Stony Brook University, affiliated with both the Institute for Advanced Computational Science and the Department of Ecology & Evolution. Her research focuses on integrating remote sensing, Bayesian inference, and machine learning to study Antarctic ecosystems. Education AB in Physics, Princeton University (2000) AM in Physics, Harvard University (2004) PhD in Organismic and Evolutionary Biology, Harvard University (2006) Heather’s work spans the development of AI-driven tools for wildlife monitoring, ecological forecasting, and conservation planning. She leads projects like the Antarctic Penguin Biogeography Project and ICEBERG, leveraging satellite imagery and computational methods to track penguin populations and biodiversity dynamics. Her research grants include significant funding from NASA, NSF, and the Pew Foundation, with recent projects focusing on AI integration in ecological modeling and Antarctic conservation. Heather has pioneered techniques for automated species detection using CNNs and developed frameworks for data-model synthesis in extreme environments. Scientific Awards Ecological Society of America Early Career Fellow (2014) National Geographic Explorer (2019) Blavatnik Laureate for Young Scientists in Life Sciences (2019) AAAS Leshner Fellow in Science Engagement (2020) She has also contributed to educational programs through courses like MAR 534 and BEE 552, emphasizing interdisciplinary training in spatial data analysis. Her lab collaborates on pan-Antarctic monitoring systems, combining unmanned aerial systems, computer vision, and high-performance computing.

Sung-Wook BaikView profile

Professor

• Image Processing
• Pattern Recognition
• Video Analytics
• +12 more

Sung-Wook Baik is a Full Professor at the Department of Digital Contents , Sejong University , and serves as Vice President of Research Affairs. He also holds an Adjunct Professor position at Ton Duc Thang University , Vietnam. His career spans over two decades, including leadership roles as Dean of Colleges of Software Convergence and Electronics and Information Engineering, Managing Director of the National Program of Excellence in Software, and Director of the Intelligent Media Laboratory (IM Lab). Education: Ph.D. in Information Technology, George Mason University (1999) M.A. in Computer Science, Northern Illinois University (1992) B.A. in Computational Statistics, Seoul National University (1987) Professor Baik’s research focuses on image processing, pattern recognition, video analytics, and smart energy systems for smart cities. His work integrates deep learning , transformers , and edge computing for applications in surveillance , fire detection , and energy load forecasting . He has published over 150 peer-reviewed papers and led international conferences, emphasizing IoT , IIoT , and multimodal data fusion . His recent publications highlight advancements in anomaly detection for smart surveillance, population projection using graph neural networks, and energy consumption prediction via hybrid deep learning. These works span journals like Pattern Recognition , IEEE Transactions on Industrial Informatics , and Applied Energy , with keywords covering Computer Science , Artificial Intelligence , and Smart City Infrastructure . Scientific Awards: Ministry of Science and ICT Minister's Citation (2020) Daeyang Academic Achievement Award (2018) Aejieon Academic Achievement Award (2016) Outstanding Research Award, Sejong University (2005) Commonwealth of Virginia Awards (2001, 1998) IEEE Contribution Award (2010) In collaboration with global teams, he advances smart surveillance and renewable energy management . His lab, IM Lab , specializes in intelligent media technologies , with patents in fire detection , energy forecasting , and person re-identification systems.

Lucas JoppaView profile

Adjunct Professor

• Climate Change
• Biodiversity
• Ecology
• +5 more

Lucas Joppa is an Adjunct Professor at the Yale School of Public Health and serves as Microsoft’s first Chief Environmental Officer . With a Ph.D. in Ecology from Duke University, he bridges technology and conservation through initiatives like the AI for Earth program, a $50 million effort to develop environmental solutions using artificial intelligence. His research integrates ecology, biodiversity, and AI to address planetary-scale challenges. Adjunct Professor, Yale School of Public Health Chief Environmental Officer, Microsoft Associate Editor in Chief, EcoSphere journal Fortune 40 Under 40 honoree Joppa’s research focuses on leveraging artificial intelligence to combat climate change, protect biodiversity, and scale environmental data systems. He advocates for technology-driven conservation and has pioneered tools for poacher detection, carbon accounting, and global biodiversity monitoring. His work emphasizes interdisciplinary collaboration between tech and environmental science. Scientific awards include being named to Fortune’s 40 Under 40, serving as Associate Editor in Chief for EcoSphere, and recognition as a highly cited researcher. He also contributes to international environmental policy, including IPBES assessments and the Global Deal for Nature.

• smart cities
• ubiquitous systems
• urban informatics
• +3 more

Rui João Peixoto José is an Assistant Professor with Habilitation at the Information Systems Department, School of Engineering, University of Minho. He holds a PhD in Computer Science from Lancaster University (2001) and teaches Ubiquitous Systems, Distributed Systems, Digital Innovation, Service Engineering, and Urban Informatics. As a Senior Researcher at Centro Algoritmi, he leads the Urban Computing R&D Group, focusing on Smart Cities, urban platforms, and locative services that blend digital information with physical/social settings. PhD in Computer Science (2001), Lancaster University Assistant Professor at University of Minho since [year] Senior Researcher at Centro Algoritmi Co-founder of 3 companies (2 University of Minho spin-offs) His research spans 150+ publications, including top journals (IEEE Computer, Sensors, Personal and Ubiquitous Computing) and conferences (Ubicomp, PerDis). Key areas: Smart Cities, urban platform design, pervasive computing, mobile payment systems, and public digital displays. Collaborations with Bosch Car Multimedia on soft smart mobility. Scientific Contributions : 98+ publications (h-index 12 in ResearcherID) 585+ Scopus citations (h-index 11) 1300+ Google Scholar citations (h-index 16) Leadership & Service : PI/co-PI in 9 projects (FP7, FET-OPEN, Portugal/CMU funded) 80+ Program Committee roles (Ubicomp, CHI, IEEE Transactions) Editorial Board member: RISTI and ADCAI journals General/TPC Chair of 2 international conferences Entrepreneurial Impact : Co-founded 3 companies, including 2 University of Minho spin-offs. Focus on pervasive computing and urban technology solutions.

Ashok DahalView profile

Assistant Professor

• Artificial Intelligence
• Geo Sciences
• Deep Learning
• +3 more

Ashok Dahal is an Assistant Professor in the Department of Applied Earth Sciences, specializing in landslide hazard modeling, InSAR data analysis, and deep learning applications for geoscience. His research integrates artificial intelligence with geological data to address challenges in environmental risk assessment. Key Research Areas: Artificial Intelligence, Geo Sciences, Deep Learning, Landslide Hazard Modeling, Computer Vision, Data Dependencies. Recent work focuses on space-time landslide modeling, physics-informed neural networks, and explainable AI for susceptibility mapping. His publications highlight collaborations across Europe and Turkey, emphasizing geohazard mitigation. Scientific Awards: EscherPrijs (2021) ITC Publication Award (2023)

Raian Vargas MarettoView profile

Assistant Professor

• Remote Sensing
• Deep Learning
• Machine Learning
• +10 more

Raian Vargas Maretto is an Assistant Professor in the Department of Earth Observation Science at the University of Twente. With a PhD in Applied Computing (2020) and an MSc in Remote Sensing (2011) from Brazil’s National Institute for Space Research (INPE), he couples deep-learning innovation with large-scale geospatial data to monitor land-use dynamics, urban deprivation and forest loss. Education: PhD Applied Computing, INPE (2020) MSc Remote Sensing, INPE (2011) BSc Computer Science, Federal University of Ouro Preto (2008) His research integrates computer vision, machine-learning and data-mining techniques with multi-sensor satellite imagery to derive actionable geographic information. Core interests encompass remote-sensing image analysis, sensor fusion, pattern recognition, GIS development, land-cover & vegetation mapping, and AI-based environmental monitoring . Across 35 recent outputs, three dominant strands emerge: (i) deep-learning architectures for semantic segmentation of deprived urban areas and Cerrado vegetation; (ii) energy-balance and vegetation-index approaches for crop evapotranspiration estimation; and (iii) space-education analytics that map European curricula to foster a sustainable space workforce. These works increasingly couple open-data philosophies with transparent AI to support SDG targets. Software & Systems: Maretto has contributed to TerraLib, TerraView, TerraME, GeoDMA and the DeepGeo package, championing open-source GIS tools. Field & Policy Engagement: He served as visiting researcher at the Ethiopian Space Science & Geospatial Institute (2022 & 2023) and has given media interviews on AI-powered deforestation monitoring.

Miguel D. MahechaView profile

Professor

• Environmental Data Science
• Remote Sensing
• Ecosystem Responses to Climate Extremes
• +6 more

Miguel D. Mahecha is a Full Professor of Environmental Data Science and Remote Sensing at the University of Leipzig's Faculty of Physics and Earth System Sciences, where he serves as Institute Head of the Institute for Earth System Science and Remote Sensing. He is also a key figure at the Remote Sensing Centre for Earth System Research, a collaborative initiative between Leipzig University and the Helmholtz Centre for Environmental Research (UFZ). His academic positions include being a Principal Investigator in the Centre for Scalable Data Analytics and Artificial Intelligence and co-spokesperson for the National Research Data Infrastructure for Earth System Sciences (NFDI4Earth). Mahecha's research focuses on understanding ecosystem responses to climate extremes and human-environment relationships during these extreme events. His work spans macro-ecological dynamics, ecosystem functioning, and the development of Earth System Data Cube methodologies that combine empirical methods with theoretical understanding. His research employs data-driven approaches and high-dimensional Earth observations to unravel complex interactions within the Earth system. His recent publications reveal a strong emphasis on compound climate extremes, Earth system data cubes, and AI applications in environmental science. Mahecha's work frequently addresses the intersection of biodiversity, climate extremes, and ecosystem functioning, with particular attention to developing novel methodologies for analyzing spatiotemporal patterns in Earth system data. Fellow of the European Laboratory for Learning and Intelligent Systems Member of the German Centre for Integrative Biodiversity Research (iDiv) Co-spokesperson for NFDI4Earth Principal Investigator in the Centre for Scalable Data Analytics and Artificial Intelligence Mahecha leads multiple significant research projects including Digital Forest (real-time forest monitoring), NFDI4BioDiversity (biodiversity data infrastructure), and XAIDA (AI for detection and attribution of extreme events). His teaching portfolio covers fundamental and advanced topics in physical geography, Earth system components, and geospatial data analysis, reflecting his commitment to training the next generation of Earth system scientists.

• Machine Learning
• Graph Neural Networks
• Water Resource Management
• +4 more

Dr. Shuming Liang serves as a Postdoctoral Research Fellow at The Data Science Institute within the Faculty of Engineering and Information Technology at University of Technology Sydney (UTS). His research bridges machine learning theory with practical applications in critical infrastructure management, particularly focusing on water distribution systems and transportation networks. His educational background includes a Ph.D. in Data Science from UTS (2020-2024), a Master of Science in Astrophysics from the Chinese Academy of Sciences (2010-2014), and a Bachelor of Science in Physics from the University of Jinan (2006-2010). Dr. Liang's research interests center on Machine Learning with specialization in Graph Neural Networks , where he develops novel frameworks for anomaly detection, link prediction, and infrastructure failure forecasting. His work uniquely integrates time-series data , geospatial data , and satellite imagery to solve real-world problems in water resource management and transportation optimization. Recent publications demonstrate his expertise in creating multi-task learning approaches that enhance the interpretability and scalability of GNNs for industrial applications. His publication trend shows increasing focus on practical implementations of machine learning in civil infrastructure, with recent work emphasizing anomaly detection in sensor networks (2025), generalization techniques for GNNs (2025), and applications in water pipe network management (2021-2024). His research consistently addresses the challenge of applying theoretical machine learning advances to solve tangible problems in critical infrastructure systems. Dr. Liang actively collaborates with industry partners through funded research projects, particularly with Sydney Water Corporation, where his work contributes to proactive maintenance strategies for water distribution networks. His research has practical implications for reducing water loss, improving infrastructure reliability, and optimizing resource allocation in urban environments. His laboratory work focuses on developing data-driven frameworks that integrate multiple data sources (pipe features, network structure, geographical information, and temporal failure patterns) to create comprehensive predictive models for infrastructure management. Current projects involve implementing these models in real-world water utility operations to enable targeted pipe inspection and renewal planning.

• Digital History
• British History
• History of Science and Technology
• +7 more

Dr. Daniel C.S. Wilson is a Lecturer in Cultural Analytics & Knowledge Systems at University College London's Department of Information Studies, with an additional appointment as Honorary Research Fellow in UCL's Department of Science & Technology Studies. He holds a current Turing Research Fellowship at the Alan Turing Institute (2023-2025) and previously served as Senior Research Associate on the 'Living with Machines' project, a major collaboration between historians, curators, and data scientists exploring British industrialization through digital methods. Wilson's research focuses on the culture and politics of data and machines from the nineteenth century to the present, combining traditional archival study with computational techniques. His primary areas include digital history, British history, history of science and technology, and computational humanities, with specific interests in language, infrastructure, and analysis of large text and map collections. His current projects employ language models and computer vision to examine historical datasets including British Library newspaper collections and Ordnance Survey maps, with attention to bias, provenance, changing language, economic history, and spatial infrastructure development. Wilson's recent publication record demonstrates consistent output in digital humanities methodology, particularly in text and map analysis. His work shows a clear trajectory toward developing computational approaches for historical research, with increasing focus on addressing representativeness and bias in digitized collections. His research bridges humanities scholarship with data science, creating new methodologies for historical inquiry while critically examining the assumptions embedded in both historical sources and contemporary analytical techniques. Professional activities include Fellowship in the Royal Historical Society (since 2022), membership in the Association of Digital Humanities Organisations (since 2019), and the British Society for the History of Science (since 2009). He has served as a reviewer for ACM FAccT since 2022, demonstrating engagement with ethical considerations in algorithmic systems. Wilson teaches techniques and theory of text analysis for large collections 'as data,' metadata systems, and digital humanities to MA/MSc students. His educational background includes a PhD from the University of London, with additional research experience at institutions including the Science Museum Group, University of Cambridge (CRASSH), and EHESS in Paris. He is fluent in French and maintains active collaborations across academic and cultural heritage institutions.

• Geosciences
• Biogeoclimatology
• Remote Sensing
• +3 more

Henri Riihimäki is a Researcher in the Department of Geosciences and Geography at the University of Helsinki, specializing in biogeoclimatic modeling. His work integrates remote sensing, field measurements, and computational methods to study Arctic and boreal ecosystems, focusing on soil-vegetation interactions, cryogenic processes, and climate change impacts. Institution : University of Helsinki Department : Geosciences and Geography Role : Researcher Email : henri.riihimaki@helsinki.fi Research Interests : His research spans remote sensing applications , soil moisture modeling , vegetation dynamics , and tundra ecosystem responses to climate change . Key methodologies include UAV campaigns, LiDAR data analysis, and topographic wetness index optimization. Scientific Trends : Analysis of 11 publications (2013–2024) reveals expertise in Arctic biogeosciences , machine learning for environmental data , shrub-soil feedbacks , and UAV-based ecosystem monitoring . Collaborative work emphasizes open data and interdisciplinary approaches.

John KerekesView profile

Research Professor

• Remote Sensing
• Imaging Science
• Hyperspectral Imaging
• +5 more

John Kerekes is a Research Professor at the Chester F. Carlson Center for Imaging Science within the College of Science at Rochester Institute of Technology (RIT). His research focuses on advancing remote sensing technology through theoretical investigations, data analysis, and modeling of remote sensing systems. Dr. Kerekes approaches the end-to-end remote sensing process as a system with application performance as the metric, developing statistical parametric models to propagate information-bearing characteristics through the remote sensing process. Dr. Kerekes holds a BS, MS, and Ph.D. from Purdue University. His research interests span remote sensing, system modeling and analysis, pattern recognition, digital imaging, and image processing. He has applied his expertise to multispectral remote sensing systems for surface land cover classification, atmospheric temperature and water vapor profiling, surface particulate matter sensing, and sub-pixel object detection and identification. He has also investigated spectral imaging for medical applications. His recent publications demonstrate a strong focus on hyperspectral imaging, methane detection, air quality monitoring, and agricultural applications. The research shows an evolving trend toward integrating machine learning with traditional remote sensing techniques, particularly in environmental monitoring and target detection applications. His work increasingly addresses practical implementation challenges in satellite and airborne remote sensing systems. Dr. Kerekes is affiliated with the Digital Imaging and Remote Sensing Laboratory (DIRS) at RIT and has secured significant research funding, including a grant from the National Geospatial-Intelligence Agency for fundamental research on imaging systems. He mentors graduate students through thesis research (IMGS-790, IMGS-890) and independent study courses (IMGS-799), focusing on advanced topics in imaging science. His laboratory work includes the SpecTIR Hyperspectral Airborne Rochester Experiment (SHARE) data collection campaigns and research on polarimetric synthetic aperture radar systems. Dr. Kerekes also contributes to major community remote sensing experiments such as ROCX 2025 at RIT's Tait Preserve, which involves deploying satellites, planes, drones, and other sensing platforms for comprehensive data collection.

Esther RolfView profile

Assistant Professor

• Statistical Machine Learning
• Geospatial Machine Learning
• Environmental Monitoring
• +3 more

Esther Rolf is an Assistant Professor of Computer Science at the University of Colorado, Boulder. Her research focuses on statistical and geospatial machine learning, emphasizing usability, data efficiency, and fairness. She explores environmental monitoring via machine learning and the impact of data representation on algorithmic fairness. Prior to CU Boulder, she was a postdoctoral fellow at Harvard’s Data Science Initiative. She earned her PhD in Computer Science from UC Berkeley, advised by Benjamin Recht and Michael I. Jordan, supported by NSF, Google, and UC Berkeley fellowships. Her work has garnered best paper awards and international recognition, including the SDG Digital Gamechangers Award. She currently teaches courses on geospatial ML and machine learning, and leads the MOSAIKS project for accessible satellite-based ML systems. She actively recruits PhD students and postdocs focused on interdisciplinary, applied ML research. Education: PhD in Computer Science, UC Berkeley (2022) Postdoctoral Fellowship, Harvard (2022) Research Interests: Esther’s work bridges ML methodology and real-world applications, particularly in environmental and social domains. Key areas include: Geospatial ML for environmental monitoring (e.g., satellite imagery analysis) Ethical AI: fairness, representation, and bias mitigation Algorithmic approaches for data-efficient, scalable systems Recent Trends in Publications: Her recent work emphasizes geospatial challenges, such as satellite data modality, global location embeddings, and policy impacts of ML-driven environmental models. She also investigates data representation’s role in model fairness across domains like poverty mapping and resource extraction tracking. Awards: SDG Digital Gamechangers Award (2023) Best Paper at ICML (2018) Best Paper at NeurIPS AI for Social Good Workshop (2019) Lab & Collaboration: Her lab at CU Boulder fosters interdisciplinary research, emphasizing collaborative, communication-driven projects. Current initiatives include the MOSAIKS project and the ML & Environment Postdoctoral Fellowship program. She teaches advanced courses on geospatial ML and machine learning theory.

Francesca OdoneView profile

Professor

• Computer Vision
• Machine Learning
• Biomedical Image Processing
• +3 more

Francesca Odone serves as a Full Professor in the Department of Computer Science, Bioengineering, Robotics, and Systems Engineering (DIBRIS) at the University of Genoa, Italy. She holds a position on the Department Board and teaches core courses including Computational Vision , Algorithms and Data Structures , and Fundamentals of Signal and Image Processing across undergraduate and graduate programs in Computer Science and Biomedical Engineering. Her research centers on Computer Vision and Machine Learning with critical applications in Biomedical Engineering . Key focus areas include markerless motion analysis for neurological disorders (particularly multiple sclerosis), video-based assessment of motor functions in spinal cord injury and preterm infants, and deep learning for medical image interpretation . She integrates robotics and signal processing to develop non-invasive clinical diagnostic tools, emphasizing practical healthcare solutions through interdisciplinary collaboration. Analysis of her 15 most recent publications (2024-2025) reveals three dominant trends: (1) Proliferation of markerless video-based clinical assessment tools for gait/motion analysis, (2) Advanced deep learning architectures (diffusion models, disentangled representations) applied to medical imaging challenges, and (3) Cross-cutting work on AI fairness/debiasing techniques. Her research consistently bridges computer vision with neurology, rehabilitation medicine, and neonatology. Professor Odone actively contributes to DIBRIS's research ecosystem through ongoing projects in biomedical computer vision, with strong connections to clinical partners. Her work demonstrates sustained focus on translating computer vision innovations into practical healthcare applications, particularly for neurological and developmental conditions.