Don’t be a dummy – use AI for field course design

Dr Mark Tupper – Institute of Science & the Environment, University of Cumbria, Carlisle, UK
Dr Ian Hendy – Institute of Marine Sciences, School of Biological Sciences, University of Portsmouth, Portsmouth, UK
Dr Reuben Shipway – General Organization for Conservation of Coral Reefs and Turtles in the Red Sea, Jeddah, Kingdom of Saudi Arabia

Academics are increasingly under heavier workloads due to funding shortages across the higher education sector, resulting in greater administrative burdens, higher stress, and poor work-life balance. According to a survey by Education Support (2021), 53% of UK higher education faculty showed probable signs of depression, 79% said they often or always need to work very intensively, 21% work an extra 2 days (16 hours) per week on top of contracted hours, and 54% have considered leaving the sector in the past two years due to pressures on mental health.

AI large language models (LLMs), such as ChatGPT, offer great promise in relieving these pressures due to their ability to generate natural language text, intuitive interface, and flexible utility. Research has shown that ChatGPT performs well at routine administrative tasks, such as generating course content, schedules and itineraries, and creating and grading assessments. However, to our knowledge, its utility as a tool for creating off-campus field courses to explore real-world experiential learning opportunities has not yet been tested. In a new study, “Field courses for dummies”, marine biologists Mark Tupper, Ian Hendy, and Reuben Shipway explore the role of LLMs in field course design. To gauge the potential to apply ChatGPT for module development, the authors created two marine-themed field courses. Within our context, a field course is considered a hands-on, experiential learning activity that takes place within a broader educational module. One of these field courses was newly developed from scratch to supplement an existing module, while the other was specifically tailored to enhance and integrate with the learning objectives of a pre-existing module. Both were designed as single-day field trips aimed at undergraduate-level students with a cohort size of approximately 60.

Through prompt engineering (the process of carefully designing and optimising input prompts to guide AI outputs), ChatGPT generated learning objectives, lesson plans, travel itineraries, equipment lists, risk assessments, and course assessments. This resulted in two competent and comprehensive field course curricula being created in an afternoon. The authors then compared the ChatGPT-generated field course with a human-designed course and found that they were remarkably similar. However, the human-designed course held practical advantages, like ensuring site accessibility and setting assessments more-closely aligned with the taught field skills – insights gained from years of experience running field courses.

While ChatGPT did most of the heavy lifting, human input from experienced field biologists was necessary to ensure that the suggested curriculum and itinerary was feasible in a field setting. For example, ChatGPT could not access tidal data for the project site, and therefore scheduled beach surveys at high tide, when the beach would not be accessible. Thus, despite ChatGPT’s powerful capabilities in generating content that can significantly reduce the time and effort in course design, the research underscores the indispensable role of human insight for optimal results. The authors therefore caution that all output requires careful expert consideration before implementation.

The study also revealed the critical importance of detailed prompt engineering, iterative refinement, and reflective feedback loops to pilot ChatGPT to effective outcomes. By detailing their workflow (see figure 1 below) and outcomes, the authors offer valuable insights into effective AI collaboration strategies, best practices for integrating AI tools in course design, and the adaptive management needed for continuous improvement. This workflow can be applied to other disciplines that involve outdoor work, such as environmental work, conservation, school trips, adventure trips, and public outreach.

Figure 1: A workflow for effective use of ChatGPT in designing field courses. Before interacting with ChatGPT, users should prepare an ‘Ingredients List’ – What, Where, When and Who. In the ‘Dummies’ example, the courses were designed for a marine biology degree (What), to the UK coast (Where), during term-time (When) for approximately 60 marine biology undergraduate students (Who). The workflow then provides a guideline for building a field course, from identifying the learning objectives to a risk assessment, and uses an adaptive management approach, where AI output is adjusted based on feedback and human expertise to improve outcomes.
In addressing the escalating workloads faced by academics due to funding shortages, this research demonstrates that ChatGPT coupled with human insight can significantly alleviate these pressures by innovating field course design, thereby bridging the gap between technological potential and practical application in higher education.

So don’t be a dummy, use ChatGPT to design your field course now!

References
Wray, S., & Kinman, G. (2021). Supporting staff wellbeing in higher education.
https://www.educationsupport.org.uk/resources/for-organisations/research/supporting-staff-wellbeing-in-higher-education/

Tupper, M., Hendy, I.W. and Shipway, J.R., 2024. Field courses for dummies: To what extent can ChatGPT design a higher education field course? Innovations in Education and Teaching International, pp.1-15.
https://www.tandfonline.com/doi/full/10.1080/14703297.2024.2316716

Dr Mark Tupper is a Senior Lecturer in Marine Biology at the University of Portsmouth and a Marine Ecosystem Scientist at CGG Services (UK) Ltd. His research focuses on fish habitat ecology, with a specialisation in coral reef fishes. He also consults extensively in the fields of fisheries management and coastal and marine environmental impact assessment. He has over 20,000 hours of fieldwork experience and field course curriculum design in coastal and marine environments. You can find out more about his research here.
@reeffishhabitat

Dr Ian W. Hendy is a Senior lecturer in Marine Biology at the University of Portsmouth. His research focuses on tropical marine biology, including mangrove forest ecosystems. He has over 20,000 hours of fieldwork experience and field course curriculum design, including work in Indonesia, Mexico, and the UK. You can find out more about his research here.
@marine_conserve

Dr J. Reuben Shipway is the Director of Partnerships, Engagement and Coordination, at the General Organization for Conservation of Coral Reefs and Turtles in the Red Sea. He is a former Lecturer in Marine Biology at the University of Plymouth, and a current National Geographic Explorer, and Editorial Board Member for the Royal Society journal, Biology Letters. He has over 10,000 hours of fieldwork experience and field course curriculum design, including work in Central America, Europe, North America, and SE Asia. You can find out more about his research here.
@ReubenShipway