Aerial photography and machine learning for estimating extremely high flamingo numbers on the Makgadikgadi Pans, Botswana

Abstract

Monitoring biodiversity over time and space is essential for effective conservation of habitats, processes, and dependent organisms. Estimating large abundances of individuals can be challenging (e.g. birds and mammals), demanding efficient and effective methods. The Makgadikgadi Pans in north-eastern Botswana have high concentrations of breeding and feeding flamingos (Phoenicopterus roseus and Phoeniconaias minor), among the world’s most important breeding sites. No published estimates of flamingos exist since 2009, with historical estimates providing limited details on methods. We developed a semi-supervised machine learning method for counting a large feeding concentration of flamingos (2 June 2019) in aerial photographs from northern Sua Pan of the Makgadikgadi Pans. We also analysed rainfall and flooding frequency and extent, using satellite imagery, estimating likely frequency of these flamingo concentrations. Lastly, we reviewed the site’s global importance as flamingo breeding habitat. Our analysis successfully provided an estimate of 372,172 to 689,473 flamingos, with methods producing over 97 % test accuracy. Uncertainty related primarily to data coverage and collection rather than methodology. This estimate underlined the Makgadikgadi Pans’ significance for flamingos, supported by a high frequency of flooding (>5:10 years). Sua Pan ranked in the top ten breeding sites for the lesser and greater flamingos in the world. These methods can be applied to other large concentrations of flamingos and other animals. Our techniques provide considerable promise for tracking flamingo populations to ensure their protection. We provide code, for use in Google Earth Engine.

Keywords

• Aerial photography
• Counting
• Flamingos
• Flooding frequency
• Semi-supervised machine learning
• Sua Pan