This repository provides the datasets and R scripts associated with the recent publication by Lilkendey et al. (2024) in Ecology & Evolution, entitled Herbivorous Fish Feeding Dynamics and Energy Expenditure on a Coral Reef: Insights from Stereo-Video and AI-Driven 3D Tracking. The study applies advanced stereo-video monitoring and AI-assisted three-dimensional tracking to examine feeding behaviour, energy expenditure, and the energetic modelling of surgeonfish field metabolic rates in coral reef ecosystems, with emphasis on the Brown surgeonfish (Acanthurus nigrofuscus) and Yellowtail tang (Zebrasoma xanthurum). The R scripts provided here include methods for cleaning three-dimensional trajectories and energetic modelling, in addition to detailed linear mixed-effects analyses of bite rates, bite distances, and their relationships with different substrate covers. The corresponding dataset, available via PANGAEA (DOI: 10.1594/PANGAEA.957634), encompasses remote underwater visual census data, bite rate and bite distance measurements, fish length records, and AI-derived movement trajectories. This repository also features an iNaturalist training dataset that aligns with FAIR data principles (Lilkendey 2023; DOI: 10.1111/ele.14311) and acknowledges the fundamental contributions of community scientists who document and identify fish species. For further details on methodologies and findings, see: Lilkendey, J., Barrelet, C., Zhang, J., Meares, M., Larbi, H., Subsol, G., Chaumont, M., & Sabetian, A. (2024). Herbivorous fish feeding dynamics and energy expenditure on a coral reef: insights from stereo-video and AI-driven 3D tracking. Ecology & Evolution. DOI: 10.1002/ece3.11070 Enquiries or collaborative proposals may be directed to Julian Lilkendey at julian.lilkendey@icloud.com.