Dr Henry Moss is a Researcher at the Department of Applied Mathematics and Theoretical Physics within the School of Physical Sciences at the University of Cambridge. His work focuses on machine learning applications in climate modeling, Bayesian optimization, and Gaussian processes, bridging computational mathematics with environmental science and chemistry. His research interests include: Bayesian optimization for environmental and chemical systems Reinforcement learning in climate modeling Gaussian processes for molecular property prediction High-throughput machine learning in scientific domains Interpretable AI for coastal flooding prediction Hybrid ML-physics modeling Dr Moss's publications highlight his contributions to federated learning for climate models, sparse Gaussian process techniques, and multi-objective optimization frameworks. These works span applications in weather prediction, chemical engineering, and oceanography. Email: hwm26@cam.ac.uk
Michael Baldea is an Associate Professor in the Department of Chemical Engineering at the University of Texas at Austin . He holds a Ph.D. in Chemical Engineering from the University of Minnesota (2006), with prior degrees from 'Babeş-Bolyai' University in Romania (M.Sc. 2001, Diploma 2000). His research group develops theoretical and computational methods for Process and Energy Systems Engineering , focusing on integrated decision-making, performance optimization, and process intensification with industrial validation. Education: Ph.D., Chemical Engineering, University of Minnesota (2006) M.Sc., Interface Process Engineering, 'Babeş-Bolyai' University (2001) Diploma, Chemical Engineering, 'Babeş-Bolyai' University (2000) Research Thrusts: Integrated decision-making in chemical/energy supply chains Process performance monitoring and optimization Process integration and intensification Key applications include grid-responsive chemical plants, intensified distillation/column designs, and renewable energy integration for building systems. Scientific Awards: Frank A. Liddell, Jr. Fellowship NSF CAREER Award (2015-2020) Moncrief Grand Challenges Faculty Award (2014) AIChE Outstanding Young Researcher Award (2017) Implementation : His group has translated research into commercial tools through partnerships with industrial test beds and is working to integrate methods into commercial simulators. They explore predictive approaches for building energy management and strategic capital investment analysis in next-generation energy systems.
Richard E. Turner is a Professor of Machine Learning at the University of Cambridge's Department of Engineering and Research Lead for AI for Weather Prediction at the Alan Turing Institute. He serves as Cambridge Lead for the EPSRC Probabilistic AI Hub and previously held roles including Visiting Researcher at Microsoft Research, Co-Director of the AI4ER CDT, and Course Director for the Machine Learning and Machine Intelligence MPhil program. Current research focuses on probabilistic machine learning fundamentals, environmental prediction (weather/climate), and spatio-temporal modeling combining deep learning with Bayesian methods Supervised 26 PhD students (13 graduated) and 7 research assistants/associates Secured over £30M in research funding from EPSRC, Microsoft, Toyota, Google, DeepMind, Amazon, and Improbable Featured in BBC Radio 5 Live's The Naked Scientist, BBC World Service's Click, and Wired Magazine His recent publications demonstrate expertise in diffusion models for PDE simulations, Gaussian Processes for environmental applications, and Bayesian methods for spatio-temporal forecasting. Key trends include climate modeling using ML, neural PDE solvers, and scalable probabilistic inference. Awards : Cambridge Students' Union Teaching Award for Lecturing; supervised Qualcomm Innovation Fellowship winner Collaborations : Microsoft Research (AI4Science), Alan Turing Institute, EPSRC Probabilistic AI Hub Turner leads the Turner Group within Cambridge's Machine Learning Group, focusing on uncertainty-aware ML for scientific applications. Current research assistants work on topics like meta-learning, Bayesian inference, and climate science applications.
Ann B. Lee is a Professor and Co-Director of the PhD Program in Statistics at Carnegie Mellon University , with a joint appointment in the Department of Statistics & Data Science and the Machine Learning Department. Prior to joining CMU, she held positions as a J.W. Gibbs Assistant Professor at Yale University and a visiting research associate at Brown University. PhD in Physics, Brown University MSc/BSc in Engineering Physics, Chalmers University of Technology, Sweden Her research focuses on statistical methodology for complex data in the physical sciences , emphasizing trustworthy inference, uncertainty quantification, and integration of classical statistics with machine learning. Recent work includes likelihood-free inference, calibrated forecasting, and diagnostics for generative models. The STAMPS research group , which she co-founded in 2018, hosts weekly meetings and public webinars. In Fall 2024, STAMPS will transition into a CMU Research Center. Recent publications span likelihood-free inference , climate modeling , and astronomy . Notable collaborations include applications to hurricane intensity guidance , galaxy redshift estimation , and cosmological parameter biases . She mentors PhD students and has advised multiple award-winning researchers, including ASA Best Student Paper Award winners. Her teaching includes advanced courses on probability, regression, and AI for climate sciences.
Rajesh Karki is a Professor in the Department of Electrical and Computer Engineering at the University of Saskatchewan’s College of Engineering. He holds a B.E., M.Sc., and Ph.D. in related fields. His research focuses on power system reliability, renewable energy integration, and microgrid resilience, with particular emphasis on addressing challenges posed by extreme weather, cyber threats, and decarbonization targets. Dr. Karki’s work spans theoretical modeling, probabilistic analysis, and practical implementation strategies for smart grids, energy storage systems, and distributed generation. His educational background includes advanced degrees in electrical engineering, complemented by professional engineering licensure (P.Eng.). His research has explored diverse topics such as wind energy curtailment mitigation, energy storage optimization, and demand response mechanisms in developing economies like Nepal. He has authored numerous peer-reviewed publications on grid resilience, reliability economics, and cyber-physical system security. Key themes in his work include: (1) quantifying the reliability value of energy storage in active distribution systems, (2) modeling cyber-physical threats to microgrids, and (3) developing frameworks for extreme weather-resilient infrastructure. Despite the volume of his publications (over 50 articles), no specific awards or grants are explicitly listed in the provided materials. His research often intersects technical, economic, and policy dimensions of sustainable energy systems.
Kishalay Mitra is a Professor at the Indian Institute of Technology Hyderabad , with affiliations to the Department of Chemical Engineering , Department of Climate Change , and Department of Artificial Intelligence . He also holds visiting professorships at Washington University in St. Louis and University of Washington, Seattle . His work in the Global Optimization & Knowledge Unearthing Laboratory (GOKUL) spans interdisciplinary optimization, machine learning, and their applications in industrial-scale engineering problems. Education : Ph.D. from IIT Bombay. Research Interests : Mitra's research focuses on optimization under uncertainty , surrogate modeling , multi-objective optimization , and integrating machine learning with physics-based models . His work addresses real-world challenges in wind energy , bioenergy supply chains , chemical process control , nanoscience , and environmental modeling (e.g., PM10 spatiotemporal analysis, forest fire prediction, and carbon capture). Article Trends : His recent publications emphasize wind energy systems (layout optimization, yaw control, forecasting), materials science (precipitate growth prediction, polymerization), and industrial processes (crystallization, grinding circuits). Techniques include neural operators , Bayesian optimization , generative adversarial networks (GANs) , and explainable AI .
Johanna Ziegel is a Professor of Statistics at ETH Zurich, Switzerland, since 2024, and a Visiting Scientist at the Heidelberg Institute for Theoretical Studies (HITS). Previously, she held positions at the University of Bern, where she was promoted to Full Professor in 2023. Her research focuses on decision-theoretically sound methods for forecast evaluation, probabilistic forecasting, risk measures in finance, and applications in meteorology, medicine, and climate science. She is actively involved in editorial roles for journals like Bernoulli , JASA: Theory & Methods , and SIAM Journal on Financial Mathematics . Education: PhD in Stereological Analysis of Spatial Structures from ETH Zurich (2010), supervised by Paul Embrechts and Eva B. Vedel Jensen. Postdoctoral research at the University of Melbourne and Heidelberg University. Research Interests: Forecast evaluation, elicitable functionals, risk measures, isotonic regression, statistical calibration, and applications in finance, climate science, and biostatistics. Her work bridges theoretical statistics with practical challenges in uncertainty quantification and decision-making under uncertainty. Advising & Collaborations: Supervised 7 PhD students and mentored several postdocs. Collaborates with the Computational Statistics group at HITS and the Oeschger Centre for Climate Change Research. Her group explores distributional regression under order constraints and novel methods for forecast comparison. Recognition: Credit Suisse Award for Best Teaching (2022), H.I.T. Program for Academic Leadership (2021–2022). Active in professional service, including the Bernoulli Society Council and editorial boards.
Filippo Maria Bianchi is an Associate Professor in the Department of Mathematics and Statistics at UiT The Arctic University of Norway, where he conducts research at the intersection of machine learning, dynamical systems, and complex networks. He is also a Senior Researcher at NORCE Norwegian Research Centre and actively contributes to the IEEE Task Force on Learning for Structured Data and the ELLIS Society. Department: Department of Mathematics and Statistics School: Faculty of Science and Technology University: UiT The Arctic University of Norway Adjunct Position: Senior Researcher, NORCE Education: Bachelor’s in Computer Engineering, Sapienza University of Rome Master’s in Artificial Intelligence & Robotics, Sapienza University of Rome (cum laude, 2012) PhD in Machine Learning, Sapienza University of Rome His research focuses on graph machine learning, time series analysis, reservoir computing, and probabilistic forecasting , with applications in energy analytics and remote sensing. He has led and contributed to numerous projects involving Arctic power grids, satellite-based environmental monitoring, and deep learning for sustainability. The recent publications reflect a strong trend in graph neural networks —particularly pooling mechanisms, spatiotemporal modeling, and explainability—alongside applications in energy forecasting, avalanche detection, and remote sensing . His work combines theoretical innovation with real-world impact, especially in Arctic and remote environments. Scientific Affiliations and Leadership: Vice-Chair, IEEE Task Force on Learning for Structured Data Member, ELLIS Society Co-founder, Northernmost Graph Machine Learning group Member, IEEE Task Force on Reservoir Computing Visiting Professor, Politecnico di Milano (2024–2025) He actively mentors students and collaborates on interdisciplinary research. He has led projects in power grid reliability, solar fault detection, and unsupervised change detection in satellite imagery . His work is supported by open-source implementations and reproducible research practices. Laboratories and Research Groups: Northernmost Graph Machine Learning group (co-founder) ARC Research Group, UiT Graph Machine Learning Group, Lugano
David J. Stensrud is a Professor of Meteorology and Atmospheric Science at Pennsylvania State University, where he has been a faculty member in the Department of Meteorology and Atmospheric Science within the College of Earth and Mineral Sciences. His research focuses on advancing our understanding of severe weather phenomena and improving numerical weather prediction capabilities. Dr. Stensrud received his academic training at Penn State, earning his M.S. in Meteorology in 1985 and his Ph.D. in Meteorology in 1992. His educational background has provided the foundation for his extensive research career focused on atmospheric dynamics and prediction. Dr. Stensrud's research spans several critical areas in atmospheric science, with particular emphasis on mesoscale meteorology , numerical weather prediction , and synoptic meteorology . He is internationally recognized for his work on ensemble forecasting , where he explores how groups of numerical weather prediction models can provide probabilistic forecasts of severe weather events. His research on convective-scale data assimilation aims to improve how observations from radar and satellites are incorporated into high-resolution weather models. Additional research interests include the physical processes behind severe weather phenomena like derechos and heavy rainfall events, the predictability of convective-scale phenomena, and the dynamics of the North American monsoon system. He has made significant contributions to understanding how urban environments influence thunderstorms and how convective systems interact with their larger-scale environment. Analysis of Dr. Stensrud's recent publications reveals a consistent focus on improving severe weather prediction through advanced data assimilation techniques. His work primarily centers on integrating radar and satellite observations into convection-allowing models to enhance forecasting capabilities for thunderstorms and other severe weather phenomena. A notable trend in his research is the increasing sophistication of ensemble approaches to address uncertainties in both initial conditions and model physics. His publications demonstrate a progression from fundamental studies of mesoscale phenomena to increasingly operational applications with potential for real-world forecasting improvements. Dr. Stensrud has served in several important professional capacities that highlight his standing in the meteorological community: Chair, Storm-scale Radar Data Assimilation Workshop, Norman, Oklahoma, October 2011 Member, NOAA/NWS Functional Weather Radar Requirements Integrated Working Team, 2012-2013 Guest Editor, Advances in Meteorology, Special Issue on "Storm-scale data assimilation and NWP", 2013 Commissioner, Scientific and Technological Activities Commission, American Meteorological Society, 2016-2017 Dr. Stensrud has authored more than 150 peer-reviewed publications and a textbook entitled "Parameterization Schemes: Keys to Understanding Numerical Weather Models." He has been actively involved in mentoring graduate students, though specific names of advisees are not provided in the available information. In collaboration with colleagues at Penn State, he helped create a 20-station environmental monitoring network across Pennsylvania with plans to expand to 50+ stations. His research has been supported by various grants that have enabled field campaigns such as the Mesoscale Predictability Experiment (MPEX) in 2013, where his team intercepted severe thunderstorms to collect critical observational data. Dr. Stensrud is involved with several research teams and facilities at Penn State, including work with the Joel N. Myers Weather Center and the Bob and Charlotte Landis Broadcast Room. His research group focuses on analyzing data from dual-polarization radar systems and developing improved techniques for assimilating these observations into convection-allowing models. He collaborates extensively with other researchers at Penn State and beyond, particularly in studies involving the interactions between urban environments and thunderstorms, and the upscale effects of deep convection on larger-scale weather patterns.
Dr. Yongchao Huang is a Lecturer (Assistant Professor) in the School of Natural and Computing Sciences at the University of Aberdeen, where he has been employed since August 2023. He also holds affiliations with the University of Oxford and the University of Cambridge through past postdoctoral and collaborative roles. He is actively involved in research, teaching, and academic service, and is currently accepting PhD students. His educational background includes: DPhil in Engineering Science, University of Oxford (2013–2017) Additional training in Machine Learning at Oxford (2015–2019) Dr. Huang's research focuses on fundamental and physics-informed machine learning, with core interests in Bayesian inference, variational methods, generative modeling (especially score-based), reinforcement learning, and interdisciplinary AI applications in mechanics, biology, energy, climate, and finance. A central theme of his work is the inference and sampling of probability densities, particularly through innovative particle-based and physics-inspired computational frameworks. He founded the Computational and Physical Learning (CPL) lab at Aberdeen in 2023. His recent publications (2020–2025) reflect a strong trend in probabilistic machine learning, with increasing focus on physics-based inference methods such as electrostatics, fluid dynamics, and material point methods. These works bridge machine learning with applied mathematics and physical simulation, demonstrating a unique interdisciplinary approach. Topics span Bayesian neural networks, acoustic wave propagation, mortality modeling, and adversarial cybersecurity. Dr. Huang has received academic recognition through invitations to serve on program committees and editorial roles: Program Committee Member, ECAI 2024 Organizing Committee, Bioinference 2024 Guest Editor, Journal of Theoretical Biology Senior Scientific Advisor to a UK firm He has supervised 57 MSc theses independently and currently supervises one PhD student. He has secured research engagement through collaborations with institutions including Oxford, Cambridge, and industry partners. His teaching includes courses such as Introduction to Software Engineering , Software Process and Management , and Computational Intelligence at Aberdeen, as well as practicals in inference at Cambridge. Dr. Huang leads the Computational and Physical Learning (CPL) lab at the University of Aberdeen, a curiosity-driven research group focused on foundational advances in machine intelligence. Though currently a solo researcher due to limited resources, the lab emphasizes end-to-end research and open collaboration. He encourages student mobility and interdisciplinary exploration.
Dan Sheldon is a Professor in the Department of Computer Science at the University of Massachusetts Amherst, holding a Five College joint faculty position with Mount Holyoke College. His research focuses on developing algorithms to address environmental challenges using large datasets, emphasizing computational sustainability. Key areas include spatial optimization for endangered species conservation, continent-scale bird migration modeling, and interpreting weather radar data for ecological insights. Methodologically, his work leverages probabilistic inference, network modeling, and machine learning. Sheldon earned a PhD in Computer Science from Cornell University and an AB in Mathematics from Dartmouth College. His postdoctoral training at Oregon State University was supported by an NSF Bioinformatics Fellowship. He co-leads the BirdCast project, an NSF-funded initiative applying novel machine learning to avian migration studies. His research affiliations include the Center for Data Science and the Computational Social Science Institute. Research interests span computational biology, machine learning, and data privacy. Notable contributions include algorithms for ecological decision-making, differentially private synthetic data techniques, and Gaussian process applications in environmental forecasting. Awards include an NSF Fellowship in Bioinformatics. Current projects integrate radar data analysis, biodiversity tracking, and privacy-preserving statistical methods. Grants include the BirdCast NSF grant and collaborations in computational sustainability. His work bridges theoretical computer science with applied ecological challenges, emphasizing interdisciplinary approaches to global-scale environmental problems.
Professor Liz Stephens is a faculty member at the University of Reading's Department of Meteorology, specializing in flood forecasting, climate variability, and disaster risk management. Her work focuses on improving hydrological and meteorological models to enhance flood preparedness and climate adaptation strategies globally. Research Interests: Probabilistic flood forecasting Climate impacts on extreme events Enhancing forecast communication for decision-makers Applications in data-scarce regions like Kenya and Uganda Key Projects: Global Flood Awareness System (GloFAS) World Weather Attribution studies Probabilistic forecast evaluation frameworks Her research bridges academic analysis with practical implementation, collaborating with international organizations like ECMWF and humanitarian agencies to translate scientific insights into actionable disaster preparedness measures.
Navid Bayati is an Associate Professor at the University of Southern Denmark, affiliated with the Institute of Mechanical and Electrical Engineering and the Centre for Industrial Electronics. He leads the Control and Protection of Smart Grids (CAP-SG) group and focuses on renewable/hybrid power systems, microgrid protection, and grid code compliance. Education: Ph.D. in Power Systems & Microgrid Protection (2020, Aalborg University); M.Sc. in Power Systems (2017, Amirkabir University of Technology) His research spans renewable energy integration , transient analysis , grid interconnection , and digital twin applications . Recent work includes machine learning for carbon emission prediction, fault localization in DC microgrids, and supercapacitor resilience in hybrid systems. Collaborations include projects like IEA Wind Task 50 and RePoSys , addressing grid renovation, life cycle assessment, and digital twin resilience. His teaching portfolio covers power electronics , energy management , and microgrid control .
Dr. Miguel Rico-Ramirez serves as Associate Professor of Radar Hydrology and Hydroinformatics at the University of Bristol's School of Civil, Aerospace and Design Engineering. His research integrates advanced radar technology with hydrological modeling to address critical water resource challenges including flood forecasting, drought management, and precipitation measurement across diverse global contexts from South Korea to Mexico City. Education: Bachelor of Engineering (Eng.) Master of Engineering (M.Eng.) Ph.D. in Engineering, University of Bristol His research program focuses on radar-based precipitation estimation, hydroinformatics, and flood prediction systems. He pioneers deep learning applications for rainfall nowcasting and develops innovative methods for uncertainty quantification in hydrological modeling. Current work emphasizes cosmic-ray neutron sensor validation, satellite-based flood mapping, and seasonal forecast applications for reservoir operations, with strong emphasis on translating research into operational water management solutions. Recent publications (2023-2025) reveal three dominant research thrusts: (1) deep learning frameworks for spatiotemporal rainfall prediction, (2) global validation of precipitation and soil moisture datasets using novel sensor networks, and (3) operational implementation of seasonal forecasts for drought mitigation in South Korea. His work consistently bridges radar meteorology with practical hydrological applications across urban and data-scarce environments. Scientific Awards: No specific awards documented in source materials Dr. Rico-Ramirez supervises postgraduate researchers in radar hydrology and hydroinformatics, with projects spanning flood early warning systems, precipitation nowcasting, and climate adaptation strategies. His research receives funding for international collaborations focused on water security challenges, particularly in drought-prone regions and data-scarce basins like the Nile Delta. Current grants support development of integrated forecasting systems combining global datasets with machine learning for extreme event management. He leads the Radar Hydrology research group within Bristol's Water and Environmental Engineering division, collaborating closely with Professor Dawei Han on hydroinformatics and Dr. Rafael Rosolem on water-climate interactions. The team maintains active partnerships with meteorological agencies and water authorities globally, particularly in flood forecasting system implementation across South Korea and Mexico.
Dr. Patrick S. Market is a Professor of Atmospheric Science and currently serves as the Director of the School of Natural Resources at the University of Missouri. He also acts as Interim Co-Director of the Missouri Water Center. His research focuses on synoptic and mesoscale dynamics, particularly winter weather, heavy rainfall, flash flooding, and severe local storms. He has contributed to advancements in precipitation efficiency studies and operational forecasting techniques. His work explores the role of artificial intelligence in weather prediction and communication, emphasizing the continued importance of human expertise in an automated forecast process. Dr. Market has secured grants for data stream maintenance and digital equity planning, and he has led educational initiatives integrating research into synoptic meteorology classrooms. Notable collaborations include projects with the National Weather Service and studies on the Ozark Plateau's topographical influence on weather systems.
