1. INTRODUCTION
Implementation of effective conservation planning relies on a robust understanding of the spatio-temporal distribution of the target species. In the marine realm, this is challenging for species that are rarely seen at the sea surface due to their extreme diving behaviour such as beaked whales or sperm whales (Perrin et al. 2009). Among these deep diving predators, the sperm whale (Physeter macrocephalus) that can display long (~45 min) and deep dives (up to 1860 m) with short surface intervals (~9 min) (Watwood et al. 2006, Teloni et al. 2008), is listed as vulnerable on the IUCN classification redlist. Depletion of this species’ global population was the result of excessive historic hunting and the current lack of complete recovery of the population worldwide (Whitehead 2002). Although numerous studies have focused on sperm whales’ spatial ecology and habitat selection (Jaquet 1996, Watkins et al. 1999, Gannier et al. 2002, Whitehead & Rendell 2004, Gannier & Praca 2007, Pirotta et al. 2011, 2020), regional assessments are still limited to the Northeast coast of Europe and the Mediterranean Sea (Gannier et al. 2002, Laran & Drouot-Dulau 2007, Laran et al. 2017b, Taylor et al. 2019, Virgili et al. 2019) despite the widespread occurrence of sperm whales in the Pacific (Davis et al. 2007, Whitehead et al. 2008) and Indian Oceans (Laran et al. 2017a, Huijser et al. 2020).
Since the establishment of the Indian Ocean Whale Sanctuary by the International Whaling Commission in 1979 (Holt 1983), an increasing number of surveys focussing on the distribution of cetaceans (including sperm whales) in this region have been conducted (Mannocci et al. 2014b, Laran et al. 2017a). Recent aerial surveys conducted in the Southwest Indian Ocean confirmed the presence of sperm whales around Reunion and Mauritius Islands (Mannocci et al. 2014b, Lambert et al. 2014, Laran et al. 2017a), but in surprisingly low densities. Low densities may be the result of spatial aggregation of false absences (Virgili et al. 2017) due to deep divers like sperm whales spending a small amount of time at the sea surface, i.e. 16-21% (Jaquet et al. 2000, Hooker & Gerber 2004). Although aerial surveys have significantly improved our understanding of the habitat use of marine megafauna in this region, this methodology can only provide a static picture of a species distribution unless surveys are regularly repeated throughout the year which is unlikely due to the cost of field campaigns and logistical difficulties (e.g. bad weather conditions). Satellite telemetry by tracking animals individually provides an alternative to assess deep divers’ movement patterns and fine-scale habitat affinities through generating animal’s trajectories in space and time. However, this approach only provides a small sample of the species distribution.
Distributed from polar regions to the equator, the sperm whale occupies a wide geographical range, but both sexes exhibit different distributions. While females inhabit mostly tropical and sub-tropical waters, adult males are mostly found at higher latitudes (except during the breeding season) in ice-free deep waters or along the edges of continental shelves (Whitehead 2018). After accompanying the females from 4 to 21 years, the young males can. leave their female relatives to migrate towards higher latitudes (Christal et al. 2011). Although migrations of this species are not regular - accordingly poorly understood - north-south migrations have been evidenced in midlatitudes but seasonal movements are less evident in tropical and sub-tropical regions (Whitehead 2003). Both topographical (e.g. slope) and hydrological (e.g. eddies) factors have been shown to influence the distribution of sperm whales in the Mediterranean Sea (Cañadas et al. 2002, Gannier & Praca 2007, Praca et al. 2009, Pirotta et al. 2011), the Atlantic (Biggs et al. 2000, Waring et al. 2001, Virgili et al. 2019), Pacific (Mannocci et al. 2014a) and Indian Oceans (Mannocci et al. 2014b).
Species Distribution Models (SDMs) have been largely used to predict potentially suitable habitats of marine species based on the relationships between the animal’s occurrences and its environment (Austin 2002, Elith & Leathwick 2009). In conservation spatial planning, the potential distribution of a species is a powerful information tool to delineate protected areas in a more efficient way (Vierod et al. 2014). However, unlike the traditional regression methods commonly used in SDMs ( (e.g. GLM), machine learning-based approaches have the ability to model complex polynomial relationships without relying on unrealistic assumptions (e.g. linearity) (Thessen 2016). In contrast to classical methods, machine learning offers a wide range of algorithms to address ecological questions and to provide robust and accurate predictions. Machine learning is therefore a promising tool in species distribution modelling and conservation planning (Elith et al. 2006).
Using data from the first satellite tags (n=21) deployed on sperm whales of both sexes inhabiting Mauritius waters (south-west Indian Ocean, Fig. 1), the predicted distribution of this deep diving species was modelled using a series of machine learning algorithms. By combining the individual satellite tracks with eight oceanographic variables (physical, surface and sub-surface predictors), our study aims at (i) investigating seasonal movements in the Indian Ocean, (ii) predicting the potential distribution and (iii) assessing the diel pattern in sperm whale diving behaviour. Since deep divers such as sperm and beaked whales might show a weak dependence on surface oceanographic characteristics (Mannocci et al. 2014b), we also included relevant sub-surface covariates describing the vertical characteristics of the water column, i.e. the mixed layer depth and the bottom temperature. These covariates are and rarely taken into account in the habitat modelling of cetaceans. By combining machine learning, state-of-the-art oceanographic variables and the first tracking dataset around Mauritius, our results provide a first baseline needed to assess the spatio-temporal distribution of the vulnerable sperm whale in a poorly known region: the Southwest Indian Ocean (SWIO).