In the context of massive datasets across disciplines, US higher education institutions provide research data services in their academic libraries and elsewhere on campuses. The core competencies to perform these emerging occupations have been developed through an extensive literature review and focus groups. This presentation will provide results from a survey validation study of current professionals to validate core competencies for research data management (RDM). The sampling frame is of data managers, stewards, curators and any related professionals from a variety of communities including, Academic Research Library (ARL) institutions, International Association for Social Science Information Service and Technology (IASIST), Research Data Alliance (RDA), Committee on Data (CODATA), Research Data Access and Preservation Association (RDAP), Earth Science Information Partners (ESIP), and others. Although US-focused, the survey findings can help determine the most important core competencies to include in any RDM curricula. The curricula resulting from the survey validation is delivered in US information schools (iSchools), but lessons learned could be used to inform curricula in any domain and address the gap in earth and environmental science education.
How to cite: Bishop, W., Murillo, A., Yoon, A., and Chassanoff, A.: Validating Research Data Management Core Competencies: A survey of US data librarianship current practices to inform the curricula, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-2847, https://doi.org/10.5194/egusphere-egu26-2847, 2026.
Each summer, the Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE) project, funded by NSF’s Harnessing the Data Revolution initiative, organizes a Summer School. I-GUIDE’s vision is to “Drive digital discovery and innovation by harnessing the geospatial data revolution.”
The I-GUIDE Summer School is a gathering of graduate students, post-doctoral researchers and early career scholars who go on a week-long intellectual journey. The Summer School is not just an event; it's a convergence of minds, ideas, and cutting-edge methodologies to shape the future of geospatial understanding. The Summer School champions the spirit of Geospatial Convergence Science, leveraging AI, and it is rooted in the belief that some of the most pressing societal challenges demand a collaborative, multidisciplinary approach.
I-GUIDE has thus far conducted three highly successful Summer Schools with themes Convergence Science in Action, Leveraging AI for Environmental Sustainability, and Spatial AI for Extreme Events and Disaster Resilience. The three Summer Schools were held at the University Corporation for Atmospheric Research facilities in Boulder, CO, and they share a few common key features:
- Convergence Science in Action: Participants navigate the intersection of various disciplines, strategically integrating knowledge, tools, and modes of thinking. The program emphasizes collaborative and professional interactions, fostering an environment where participants learn to work comprehensively on convergence science problems.
- Interactive Learning: Participants engage in a week-long immersive experience, collaborating with I-GUIDE members to develop novel solutions to computation- or data-intensive geospatial data science challenges. They delve into geoethics, geo-enabling reproducible and open science, geovisualization, and the latest in geoAI via cloud and high-performance computing.
- Diverse Application Areas: Each year, the participants address critical topics such as climate change, biodiversity, water security, sustainable development, changes in wildland-urban interface, social science data and ethical implications.
- Integration of Ethics: Ethical considerations, including Collection Bias and Limitations, Missing Perspectives, Assumption of Homogeneity, and Unintended uses.
- Independent External Evaluation: Conduct surveys, focus group interviews, and use other evaluation tools to capture participant feedback to improve learning outcomes through continuous evaluation and refinement.
- Ongoing Engagement: Participants continue to stay engaged with the I-GUIDE project by participating in various events and activities, including attending and presenting at the I-GUIDE forum and giving talks to the broader community via the Virtual Consulting Office.
In this presentation, we will provide an overview of the Summer Schools, along with relevant highlights, key outcomes, and the lessons learned. We will discuss the geospatial, computational and AI/machine learning, and collaborative working skills the participants learn and apply to work on the projects, along with the incentives I-GUIDE provides for the participants’ success.
How to cite: Ramamurthy, M.: The I-GUIDE Summer School: An annual learning experience that promotes geospatial convergence science and AI to tackle complex scientific and societal challenges, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-8543, https://doi.org/10.5194/egusphere-egu26-8543, 2026.
Understanding climate change relies on sustained observations of Essential Climate Variables (ECVs), as defined by the Global Climate Observing System (GCOS). As access to ECVs has expanded in scope and duration, users are increasingly confronted with the complexity of these datasets, including longer time series, different data structures, multiple product versions, and uncertainty estimates.
To remove common technical barriers, such as installing software and coding libraries or, locating and downloading large datasets, the European Space Agency’s Climate Change Initiative (ESA-CCI) developed a cloud-based, pre-configured JupyterLab environment designed to allow learners to begin working with satellite-derived ESA-CCI climate data within minutes.
This pre-configured JupyterLab environment supports users by integrating simplified access to decades-long global records of the 27 satellite-derived ESA-CCI ECVs into the ESA CCI Toolbox, a dedicated Python package specifically designed for ESA-CCI data that provides ready-to-use functions, allowing users to focus on visualising and analysing climate signals rather than writing custom code from scratch.
We present this environment as the foundation for a series of training events that have successfully engaged diverse audiences, including students, early-career researchers, and non-specialist stakeholders1. Through guided notebooks that walk learners through accessing ESA-CCI data, filtering and aggregating variables, visualising spatial and temporal patterns, and exploring uncertainties and data quality flags, learners gain hands-on, reproducible climate data analysis experience while deepening their understanding of the significance of satellite-derived ECVs and their role in monitoring and interpreting climate change. Our presentation will give the opportunity for conference participants to explore the JupyterLab environment during the PICO session.
1 https://climate.esa.int/en/climate-change-initiative-training/training-sessions/
How to cite: Maroini, A., Beck, L., Connors, S., Fincke, T., and Pechorro, E.: Building Foundational Climate Data Skills Through Hands-On Training with ESA-CCI's Essential Climate Variables, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-12247, https://doi.org/10.5194/egusphere-egu26-12247, 2026.
Geospatial data are increasingly available openly online, and often they are accessible in multiple ways, including web application programming interfaces (API) by the Open Geospatial Consortium (OGC). However, researchers often continue to rely primarily on manually downloading datasets to their laptops for their daily research activities. This workflow has some disadvantages. For example, if the input data updates often, making sure that all the researchers working on the topic have the exact same dataset available is a manual and an error-prone process. The use of web APIs could provide help for various use cases but requires some IT knowledge that many substance experts may lack.
To address this challenge, we developed a set of Jupyter Notebook examples designed to support researchers in accessing, exploring, and analyzing geospatial data from APIs in both virtual and local computing environments. The notebooks demonstrate and compare multiple approaches for directly accessing vector, raster, and point cloud data, as well as associated metadata records. We test the notebooks on a course for PhD students related to the Digital Waters Flagship by the Research Council of Finland and evaluate their effectiveness using a questionnaire for the course participants.
With the proposed approach, we aim to lower technical barriers and facilitate the integration of distributed data into existing research workflows. Ultimately, these practices can support the creation of digital twins of water resources and contribute to intelligent and sustainable water management.
Keywords: geospatial data, data infrastructures, Jupyter notebook, data space, technical barriers
How to cite: Imangholiloo, M., Carter, E., and Mäkinen, V.: Improving the Usability and Adoption of Digital Data Solutions: An Example for Researchers in the Digital Waters Flagship and PhD Pilot , EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-12625, https://doi.org/10.5194/egusphere-egu26-12625, 2026.
Today’s geoscience challenges and opportunities, such as those associated with environmental health, energy production, mineral extraction, fresh water and natural hazards, demand that public employees, private sector workers and researchers have skills across the fields of geology, geophysics and computer science. In addition, the integration of computing methods into global culture underscores the need to train professionals that ask key questions and make informed decisions about their best uses. In the context of geosciences, it is critical that people with an understanding of the science manage how computing methods are used to select, store, analyze and organize data, create digital public interfaces, and run models. While challenging, this provides opportunities to expand and renew geoscience education in order to promote its relevance into the future. In light of this, San José State University (SJSU) in San José, California USA, is launching a new bachelor’s degree titled ‘Computer Science and Geology’ and a new master’s degree titled ‘Computational Geoscience’ aimed at training students in both geoscience topics and computer science skills.
We have designed these programs to provide an integrated educational experience in quantitative methods, computer programming and the gathering, analysis, storage and sustainable management of large environmental, geological, and geophysical data sets. The degrees at both educational levels include an array of courses and broad faculty expertise in the separate departments of Computer Science and Geology at SJSU in data analysis, machine learning, artificial intelligence, geological and geophysical modeling across a range of geoscience topics, and natural hazards assessment. These degrees aim to equip students with applied skills to meet a growing workforce demand, and also ensure that this workforce recognizes the possibilities, limitations and dangers of computing tools and methods. The presence of SJSU in the heart of Silicon Valley, SJSU’s role in the U.S. university system as a primarily undergraduate serving institution, and the success of SJSU at transforming students’ lives through career advancement make this a positive place to launch these interdisciplinary degree programs. Through this presentation, we also hope to learn more about best practices and challenges of initiatives and programs at other universities to help guide the development of these degrees and best meet the needs of students and the future research, public service and private sector workforces.
How to cite: Madden, E. H., Blisniuk, K., Gabet, E., and Ishigaki, G.: Motivations, goals and design of new interdisciplinary Computer Science and Geology degrees at the bachelor’s and master’s levels, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-14682, https://doi.org/10.5194/egusphere-egu26-14682, 2026.
The accelerating complexity of global water challenges—driven by hydrologic intensification, a growing and urbanizing population, and proliferation of observational data—demands a new generation of water‑domain researchers who are both computationally fluent and capable of critically integrating artificial intelligence (AI) into scientific workflows. Yet, most geoscience doctoral programs provide limited training in open, reproducible computational methods, and generic AI tools often underperform in specialized environmental domains while lacking transparent attribution of sources. To address these gaps, the Digital Waters Flagship initiative designed and implemented an innovative doctoral‑level course that integrates open‑science software training with student‑driven co‑development of a domain‑adapted large‑language model (LLM) for hydrologic research assistance.
The course employs a flipped‑classroom model within the Digital Waters Virtual Research Environment (VRE), where students learn standardized, reproducible workflows using a repository structure composed of six core elements spanning data access, processing, modeling, visualization, and computational environments. Exceptional student repositories are publicly disseminated as open digital water use cases. In parallel, doctoral researchers participate in the co‑design of a hydrology‑focused research chatbot, DIWA ReChat, which is trained on authentic student‑generated workflow components and equipped with automatic knowledge‑source attribution to ensure transparency and proper crediting of contributions.
Course outcomes are evaluated through (1) pre‑/post‑assessment of computational competency, (2) evidence of improved reproducibility enabled by shared VRE infrastructure, and (3) empirical improvements in domain‑adapted LLM performance based on both conventional accuracy metrics and student‑designed AI efficacy criteria. Together, the course and chatbot development process demonstrate a scalable model for integrating open‑science education with responsible, domain‑aware AI tool creation. This work highlights a pathway for cultivating computationally capable researchers who can both leverage and critically evaluate AI in support of robust, transparent hydrologic science.
How to cite: Carter, E., Rostami, M., Culler, E., Abubaker, O., Imangholiloo, M., Pihlajamäki, M., Taka, M., Koivusalo, H., Alo-Aho, P., Martilla, H., Rasti, M., Kettunen, P., Keskinen, M., Mäkinen, V., Oksanen, J., Alho, P., and Klöve, B.: Co-developing research-assisting AI for water resources professionals: the Digital Waters Flagship’s digital methods course , EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-16396, https://doi.org/10.5194/egusphere-egu26-16396, 2026.
Digital geoscientific and geospatial datasets are rapidly growing in both number and size. These data present powerful new resources for understanding the evolution of the earth, but working with them requires computational skills are not part of typical geoscience curricula at universities. To leverage the power of these growing geoscientific and geospatial data, students need targeted educational resources that provide basic computational skills.
The new textbook Introduction to Python for Geographic Data Analysis provides a framework for learning to work with (geospatial) datasets of varying size from loading the data to producing interactive visualizations of processed data. Part 1 of the book covers the basics of programming using the Python language, introducing both programming concepts and their Python syntax. It also covers the analysis of tabular data using the pandas Python library and the basics of data visualization. Part 2 introduces working with geospatial data, including fundamental geospatial concepts, working with vector and raster data, geospatial data visualization, and loading data from online sources. Part 3 includes several case studies that build on things presented in the first two parts to demonstrate what can be done with the readers’ new skills. Finally, the appendices provide information about best practices in programing, version control with git and GitHub, and other practical coding tips that promote open, reproducible science.
The book materials are freely available online at https://pythongis.org, and we anticipate that hard copies of the book will be available later in 2026. We hope the book will appeal to a broad range of “geo” scientists, including teachers who provide courses on introductory programming or data analysis for geology and geography students, those interested in learning to interact with and batch process large datasets, and those interested in finding open-source alternatives to commercial GIS software packages.
How to cite: Whipp, D., Tenkanen, H., and Heikinheimo, V.: Introduction to Python for Geographic Data Analysis: A new, open resource for teachers and learners, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-19756, https://doi.org/10.5194/egusphere-egu26-19756, 2026.
We introduce a textbook for climate modellers and scientists seeking to learn AI.
Weather and Climate: Applications of Machine Learning and Artificial Intelligence provides a comprehensive exploration of machine learning in the context of weather forecasting and climate research. The authors begin with an introduction to the fundamentals and statistical tools of machine learning, followed by an overview of various machine learning models. Emulation and machine learning of sub-grid scale parametrizations are discussed, along with the application of AI/ML in weather forecasting and climate models. Next, the book delves into the concept of explainable AI (XAI) methods for understanding ML and AI models, as well as the use of generative AI in weather and climate research. It explores the interface of data assimilation and machine learning for weather forecasting, showcasing case studies of machine learning applied to environmental monitoring data. The book concludes by looking ahead to the future of ML and AI in climate and weather-related research, providing references for further reading. This comprehensive guide offers valuable insights into the intersection of machine learning, artificial intelligence, and atmospheric science, highlighting the potential for innovation and advancement in weather and climate research.
How to cite: Driscoll, S., Hunt, K., Mansfield, L., Swaminathan, R., Wei, H., Bach, E., and Peard, A.: Textbook and code: AI for climate scientists, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-20494, https://doi.org/10.5194/egusphere-egu26-20494, 2026.
