Modelling helps understand the physical mechanisms of change, the links between different mechanisms and components, extends the predictive capabilities of research, encouraging cross-disciplinary collaboration between studies of all aspects of the Earth system. In concert with advances in Earth system modelling, the rise of Artificial Intelligence (AI) across the geosciences makes it an attractive tool for large-scale Earth system studies. The cross-disciplinary, integrative approach of the ESM-AI forum will provide the capacity to develop new avenues of research into poorly understood linkages and feedbacks within and between the atmosphere, ocean, biosphere, cryosphere and solid earth. It will also allow to tackle applied interdisciplinarity aspects of climate change and related impacts on, for example, human health, ecosystems, natural resources. The forum will provide the ideal framework in which scientists with different skills will be able to approach problems from a coherent and holistic perspective.
William Harcourt (University of Aberdeen)
Will Harcourt is an Interdisciplinary Fellow at the University of Aberdeen leading the development of digital twin technology applied to the Arctic cryosphere. He studies glacier dynamics across the Arctic using remote sensing, artificial intelligence and close-ranging sensing methods. He is developing tools to construct digital twins of Svalbard’s cryosphere utilising Earth Observation and in situ data. This work aims to understand the interconnections between Earth system components to better understand Arctic environmental change. Will's research interests span across multiple disciplines, including glaciology, remote sensing & Earth Observation, data science, artificial intelligence, Arctic science and many more.
Massimo Bollasina (University of Edinburgh)
Massimo Bollasina is a Reader in Atmospheric Science at the School of GeoSciences, U. Edinburgh. He studied Physics and then worked in Milan, Italy, then moved to the US as a scientist at the University of California, San Diego. He then completed a PhD in Atmospheric and Oceanic Sciences at the University of Maryland College Park in 2010 and conducted cutting-edge research at the NOAA/Geophysical Fluid Dynamic Laboratory, Princeton. He then moved to Edinburgh in 2013 first as a Lecturer, then as a Senior lecturer and finally Reader. His research focuses on mechanisms of climate change and variability at the regional scale using global climate models and observations. He studies changes in extremes, and variability, including the role of anthropogenic aerosols and atmospheric teleconnections. He has previously co-led the SAGES Centre for Earth System Dynamics since 2016.
Marian Scott (University of Glasgow)
Professor Scott is a Professor of Environmental Statistics in the School of Mathematics and Statistics at the University of Glasgow, and has been an academic at the university for more than 30 years. She is an expert in developing novel spatio-temporal statistical methodology, and has over 200 publications and substantial grant funding (over £8 million as PI and CoI). Her research spans 2 main areas:
Professor Scott has served on a number of advisory groups and policymakers including. She won the Barnett award of the RSS in 2019, the EMS Impact award in 2021 and the RSE Lord Kelvin medal in 2024. Prof. Scott is a member of the scientific advisory Committee of DEFRA, NatureScot, Scottish Science advisory committee and chair of the EU scientific committee on environment, health and emerging risks to the current day. She has also held honorary appointments with IAEA, and CSIRO.
Amy Gilligan (University of Aberdeen)
Amy Gilligan is a Lecturer in Geophysics at the University of Aberdeen. She uses geophysics data, primary passive seismic data, to understand tectonic and environmental processes that are happening on Earth today, and how these have evolved over geological history. This has included deploying seismometers in Scotland, Borneo, Canada, Iceland, the USA, and Cyprus, and developing seismicity catalogs from local earthquakes and seismic velocity models for a variety of tectonic settings. She uses deep learning methods to develop more efficient workflows for processing and analysing the large datasets found in seismology. Amy completed her PhD at the University of Cambridge, focusing on mountain building and the structure of the lithosphere in central Asia, with a focus on the Tien Shan and the western Himalayas and Tibet. She then undertook a postdoc at Imperial College, London where her research focused on the seismic structure of Eastern Canada, spanning 3 billion years of Earth’s geological evolution. She moved to the University of Aberdeen in 2016, first as a PDRA, then as a RAS independent research fellow, and was appointed as a lecturer in 2020. At Aberdeen, her research has focused on understanding post-subduction processes in northern Borneo, and the role the Highland Boundary Fault has played in the building of Scotland. Amy is a former Outreach officer for the British Geophysical Association, and she regularly undertakes outreach activities with schools and at public events in north east Scotland and online.
Vahid Akbari (University of Stirling)
Vahid Akbari received the PhD degree in physics with a specialization in radar remote sensing from the UiT—The Arctic University of Norway, Tromsø, Norway, in 2013. Since 2014, he continued his research in radar remote sensing and machine learning as a Postdoctoral Research Fellow with the UiT—The Arctic University of Norway, the Norwegian Institute of Bioeconomy Research, Akershus, Norway, and the University of Stirling, U.K. Since 2023, he has been a Lecturer (Assistant Professor) in data science/artificial intelligence with the University of Stirling. He is a member of the Data Science and Intelligent Systems (DAIS) and Earth and Planetary Observation Research Groups at Stirling University. He is also a Council Member of the Remote Sensing and Photogrammetry Society (RSPSoc), U.K.
His primary research interests revolve around the intersection of radar remote sensing and statistical modeling/machine learning, with a particular focus on the applications in environmental monitoring. His research interests lie at the intersection between machine learning and Earth Observation for environmental monitoring. Specifically, he has focused on the applications of Interferometric SAR (InSAR) for land subsidence monitoring and Polarimetric SAR (PolSAR) for target detection, change detection, and land cover classification. Additionally, his work involves developing novel methods in machine learning, signal and Image processing, and data analytics for multidimensional SAR data. Furthermore, he is actively engaged in the field of big data analytics with SAR for forestry, glaciology, and agriculture monitoring. In summary his research is focused on the following area:
Sebastian Gerhard Mutz (University of Glasgow)
Sebastian G. Mutz is a senior lecturer at the University of Glasgow. He received his doctorate in climatology at the University of Würzburg (Germany) and completed his habilitation (the highest academic degree attesting research and teaching excellence) at the University of Tübingen (Germany). He investigates climate change and Earth system dynamics and focuses primarily on the interactions between climate and the Earth’s surface at different spatial and temporal scales. His research tools include process-based models (e.g., global climate models), empirical-statistical models, and techniques from AI. He’s an advocate of „open science“ and multilateral collaboration, and an active member of the European Geosciences Union (EGU) and its Outreach Committee. He serves as a topical editor for the journals Earth System Dynamics and Geoscience Communication. Recent outreach efforts include the development of open and accessible educational materials about climate science and Earthquakes.
Read a summary of our 2024 EARTH-MAI Workshop Summary
Click to contact the forum co-leads or the forum mailing list:
Existing members can complete this form to register for Earth System Modelling & Artificial Intelligence (ESM-AI) mailing list. New members must complete a membership application form.
