Enhancing Photo-Identification

of Indo Pacific Bottlenose Dolphins (Tursiops aduncus): A 360° approach integrating boat-based and underwater photography for improved accuracy and sighting counts in the Northern Red Sea, El Gouna, Egypt.

Photo-identification is fundamental to marine mammal research, with traditional methods relying on dorsal fin photographs of Odontoceti (particularly Delphinidae) and fluke photographs of Mysticeti. Occasionally, features such as pectoral fins or body markings are utilised. Dorsal fin identification is effective, though it has limitations, including changes in dorsal fins due to age, health, and environmental conditions. Determining the number of individuals in closely associated groups can be challenging when dorsal fins are obscured or resemble one another. Furthermore, misidentification may arise due to photographic quality or observer bias. This study investigates whether integrating underwater photographs enhances photo-identification accuracy of Indo-Pacific bottlenose dolphins (Tursiops aduncus) in the Northern Red Sea, Egypt.

The dataset, collected by Dolphin Watch Alliance (DWA), includes surveys from 2019 and 2023 that combined boat-based and underwater photography. Long-term engagement with the local dolphin community enabled DWA to capture detailed close-range underwater photographs, providing a comprehensive 360-degree view of the individuals by including multiple body features. We compared identification results across three key metrics: the number of positively identified individuals, the accuracy of individual identifications, and group size counts. Paired t-tests and Wilcoxon signed-rank tests were used to evaluate the impact of incorporating underwater photographs compared to relying solely on boat-based photographs for these metrics and their overall accuracy. Preliminary analysis suggests that including underwater images increases identification accuracy by capturing specific body features, such as body patterns, scars, and unique markings, which are not visible in boat-based images. This new method is particularly useful for distinguishing individuals with similar dorsal fin shapes, preventing misidentification, and improving group size estimates. Additionally, more individuals can be positively identified, leading to more accurate population size estimates and demographics. This research aims to establish a new standard in photo-identification methods, improving population assessments and advancing protective strategies for dolphin populations.

Download