Abstract:

The practical study of riparian and wetland vegetation at postgraduate level faces several challenges, including heterogeneous botanical background knowledge among students, limited time for fieldwork and the need to work with real, spatially explicit data for management and restoration. This contribution presents the design and preliminary outcomes of an educational innovation project that integrates the citizen science platform iNaturalist, supported by artificial intelligence (AI)-based image recognition, into MSc courses on riparian vegetation and wetlands with modules focused on applied botany. Here, iNaturalist works as a virtual field notebook, enabling students to document plant assemblages along riparian and wetland case studies, through georeferenced photographic observations accompanied by basic metadata.

The use of iNaturalist allows a more autonomous learning process, supported by the community feedback and the AI-generated suggestions, that help refine identifications under the instructor’s supervision. The activities are embedded in field-based practicals and complemented with short in-class briefings on iNaturalist, good practices for biodiversity documentation, and principles of data quality. Evaluation of the learning action combines platform participation metrics with pre- and post- questionnaires on perceived competence in plant identification, confidence in using digital tools and attitudes towards the role of citizen science in environmental monitoring and management.

This activity pursues a strong student engagement, enhances observational skills and greater autonomy in dealing with taxonomically challenging plant groups, especially among participants with limited prior training in plant systematics. Using iNaturalist as the axis of learning for riparian and wetland vegetation in this short course can strengthen applied botanical skills, and ultimately generate reusable biodiversity data relevant to conservation, providing a scalable model for other postgraduate courses focused on vegetation assessment.

Keywords:

Machine learning, artificial intelligence, AI, gamification, citizen science, digital learning tools, science education.