Monitoring aesthetic value of the Great Barrier Reef by using artificial intelligence to score photos and videos
Led by: Prof Susanne Becken, GU
This project addresses the urgent need to understand and monitor the aesthetic value of the Great Barrier Reef. Focusing on the fast-changing underwater systems of the Reef, this research will use advanced technology (including eye tracking and heart rate measurement) to elicit what environmental and experiential attributes contribute to aesthetic value. A Big Data platform using artificial intelligence will be created to assess large volumes of visitorsupplied imagery and to map aesthetic value across space and time.
The Great Barrier Reef as a UNESCO World Heritage site is inscribed for multiple criteria, including its outstanding heritage value that includes significant aesthetic characteristics that are important to Australians and visitors, now and in the future. Aesthetic values, like ecological values, are under multiple pressures and better understanding of what constitutes aesthetic value, how it can be measured, and how environmental changes affect value is imperative.
Aesthetic value is referred to in the original listing of the GBR as a World Heritage Area, the Burra Charter (2013), the Great Barrier Reef Region Strategic Assessment, and the Reef 2050 Long-Term Sustainability Plan. The 2012 UNESCO mission recommended that further work is required to understand the aesthetic value of the GBR, as a sensory perception of environmental attributes, influenced by cultural and personal factors. The GBR’s “superlative natural beauty” (Criterion vii) extends to above and underwater landscapes and ecosystems. This project focuses on underwater aesthetic value because it is changing most rapidly and is at acute risk from deterioration in water quality, ocean acidification, coral bleaching, and biodiversity loss. This research could be expanded later to include islands, coastal morphology and aerial vistas.
How Research Addresses Problem
This proposal responds to the increasing role that citizen science can play in the monitoring of natural assets (Becken et al., 2016). Users of the GBR share substantial amounts of imagery (photos and videos) via channels such as instagram, twitter, flickr, weibo and youtube. The images give important clues about what “matters” to Reef users. Using material provided by humans is an anthropocentric approach that accepts that aesthetic value is a human concept arising from interactions between nature and people. Photographic imagery/videos of users’ experiences in the GBR contain information on the environmental and experiential attributes of aesthetic value (Johnston et al., 2013).
To measure which elements of a simulated marine situation attract people’s attention and trigger an emotional response, this project employs a set of laboratory-based methods (Scott et al., 2016) for testing visual stimuli. The development of material will be informed by experts and findings from a complementary research team, and existing research on marine systems (see Haas et al., 2014). The objects (e.g. fish), attributes (e.g. colour) or relations (e.g. fish with coral) that are important to define beauty, naturalness, discovery and other dimensions will be measured in an ‘objectified’ way. This knowledge will then inform the development of algorithms and deep learning (using artificial intelligence) for automated analysis of imagery (proof of concept).
Theoretically, and as found by Johnston et al. (2013), attributes associated with aesthetic value largely reflect the environmental values for which the GBR is inscribed under other criteria. Understanding the relationships between aesthetic value, ecological health and visitor satisfaction is crucial for future management of the Reef. Visitor satisfaction can be approximated through the sentiment analysis being developed in an existing NESP-funded project, and this project provides further important building blocks for future automated monitoring of all three dimensions.
Alignment with NESP Research Priorities
2b) Development of a method to be adopted by the Reef 2050 Integrated Monitoring and Reporting Program (RIMReP) to monitor and assess aesthetics in the GBRWHA. Define/determine how these relate to the ecological health of the Great Barrier Reef environment.
Aesthetic value; Artificial intelligence; Imagery; Deep learning; Attributes.
This project is jointly funded through GU, TTNQ and the Australian Government’s National Environmental Science Programme.
Markers are not an exact position of where the research is taking place, they are only to be used as a guide to the general area in which it is being carried out.
Science Day, 20th November, Townsville