Animal migrations are among the most spectacular phenomena in the natural world. Although research has focused on larger vertebrates, there are a number of examples of impressive long-distance migration among small insects. Perhaps the best known is that of the eastern Monarch Butterfly (Danaus plexippus) which completes a multi-generational migratory circuit between natal sites in Canada and the United States and wintering sites in Mexico [1]. It has been long suspected that several species of dragonfly also undertake long-distance annual migrations. One dragonfly species in particular, the Globe Skimmer or Wandering Glider (Pantala flavescens) is widely distributed throughout the tropics and many temperate areas, and is thought to undertake extensive migrations following the Inter-tropical Convergence Zone (ITCZ). This meteorological phenomenon is marked by a band of clouds around the globe near the equator, which moves north and south with the seasons. For a dragonfly, Pantala flavescens has a remarkably short larval life (34–43 d, [2], [3]), allowing it to breed in the ephemeral freshwater pools and floods produced by ITCZ rainfall. But even with such a brief larval life, when the adults emerge, the ITCZ has moved on. The adults are believed to migrate to the latitude where rains are falling by taking advantage of the converging air masses of the ITCZ. Indeed, P. flavescens has been categorized as an obligate ITCZ migrant [4]. However, any independent support of such continental-scale movements was lacking until it was proposed that P. flavescens completes a multi-generational migratory circuit encompassing India and eastern Africa [5]. That study documented regular movements of large numbers of this species through the Maldives during October-December, when individuals are presumed to be en route from India to east Africa. These movements coincide with favorable high-altitude winds from the north east associated with the ITCZ, and the trans-oceanic migration was supported by reports of arrival phenology of P. flavescens in southern India, Seychelles and East Africa [5]. However, supporting evidence remains largely circumstantial, and the small size of the insects precludes the use of transmitter technology to track population movements directly ([6], but see [7]). Fortunately, the measurement of intrinsic isotopic markers in metabolically inert tissue like wing chitin now allows the tracking of migratory insect populations through the use of continental patterns in stable isotope values of inorganic and organic substrates [8], [9].

We used stable-hydrogen isotope (deuterium, δ²H) values in wing chitin of two samples of migrating P. flavescens that were collected in the Maldives (following “fall out” in December 2009 and November 2010) to infer their natal origins, based on well-known spatial patterns of δ²H in precipitation and in major surface waters across the Indian subcontinent. Pantala flavescens arrives in Maldives across the ocean from southern India [5], presumably having been bred in ephemeral water bodies fed by the seasonal (June to September) monsoon rains of the subcontinent. We therefore expected our samples to reveal a southern or central Indian origin.

Both the surface water (Figure 1, Table S1,) and July-September monsoonal rain (Figure 1, Table S2) showed similar δ²H patterns, with peninsular India generally having considerably higher δ²H values compared to the low δ²H values in the mountainous regions farther to the north. Our November sample of P. flavescens (δ²H_wing = −115±17 ‰, n = 22, range −83 to −148 ‰) did not differ from the December sample (δ²H_wing = −118±15 ‰, n = 27, range −89 to −151 ‰). The overall mean of −117±16 ‰ corresponded to predicted natal waters of −81 ‰ (range −118 to −44 ‰ [9]). Focusing largely on India for which our water isotope data were most complete, these results are consistent with our sample population of dragonflies originating at least as far north as northern India. Considering the range of the species and the nature of the precipitation isoscape for Asia, the sample of P. flavescens could have also derived from farther north and east along a similar band of latitude as the putative northern Indian origins. Such inferences of origin are conservative since any evaporation from ephemeral ponds would tend to isotopically enrich remaining waters in ²H, or the impression of more southerly origin. We depicted the potential origin in India of our population of dragonflies using a likelihood-based assignment procedure which confirmed northern origins based on a surface water and precipitation model (Figure 2).

Pantala flavescens arrive in Maldives during October-December, and are thought to originate in India [5]. We therefore predicted that our stable isotope results would confirm an Indian origin for our Maldivian samples of P. flavescens. While this prediction was indeed supported within the context of considering only possible Indian origins, both of our Maldives populations clearly originated from the far north of the subcontinent rather than from southern or central India.

This northern subcontinental origin is of interest for several reasons. First, the northern origin of P. flavescens arriving in Maldives extends the distance that they must be flying, not only to reach the Maldives, but also to complete the final leg of the intercontinental, multi-generational migratory circuit proposed by Anderson [5]. He suggested that these dragonflies used the seasonally alternating monsoon winds to follow the ITCZ, and breed in the short rains of equatorial East Africa in October–November; the summer rains of southern Africa in December–February; and the long rains of East Africa in March–May; before returning to India with the south-west monsoon to breed in June–July. Anderson [5] estimated that the distance covered (by perhaps four generations) in such a circuit would be of the order of 14000–18000 km. With our study suggesting that southwest monsoon breeding is concentrated at least as far as the north of the Indian subcontinent, those distances must be considered minima. The average distance covered may be closer to 18000 km, and some circuits possibly even longer. Furthermore, individual P. flavescens migrating from the northern subcontinent to East Africa via the Maldives must be flying in excess of 6000 km, including a trans-oceanic crossing of 3500 km. This is an extraordinary feat for a 5 cm long insect, and is, to the best of our knowledge, by far the longest regular single-generation migration documented for any insect.

Secondly, while the most parsimonious natal area for our samples of P. flavescens was northern India or Nepal, they could in fact have come from even further north and east. Certainly, from a regional perspective, wide areas of central Asia north of the Himalayas have mean annual precipitation δ²H low enough to qualify as potential geographical origins for our samples as do the mountainous regions directly to the east of the Indian region we have depicted in Figure 2 ([11], http://www.waterisotopes.org). This raises the intriguing possibility that at least some P. flavescens might complete a trans-Himalayan migration. This species is known to fly higher than any other odonate [4], with several high-altitude records up to 6300 m in the Himalayan region [4], [12], [13].

Thirdly, our results raise an interesting question: if our two populations are representative, then why are P. flavescens arriving in Maldives in November-December from the far north of the subcontinent, and not central or southern India? One possible answer follows from Anderson’s [5] suggestion that the dragonflies appearing in Maldives in October-December are the offspring of individuals that crossed the Arabian Sea, from East Africa to the Indian subcontinent, in June–July. Those dragonflies are able to make that crossing with the aid of the southwest monsoon winds. But (due the effects of Coriolis force) only in northern India do these winds travel directly from East Africa; the southwest monsoon winds arriving on the southwest coast of India originate over the southern Indian Ocean ([14], Fig. 1a). Therefore P. flavescens might only be transported in large numbers from East Africa to northern Indian subcontinent, and not to central or southern India.

In conclusion, this study supports the hypothesis of Indian subcontinent origins of P. flavescens arriving in Maldives during November–December, and has extended the likely distances over which they migrate while recognizing that individuals may well be coming from natal origins even further north and east. We have further provided indirect support for the proposed migration of P. flavescens across the Arabian Sea from East Africa to northern Indian subcontinent during June–July. The use of stable isotope analyses to further unravel the behavior of these migratory dragonflies has been amply justified, and further studies of P. flavescens involving additional areas, seasons and isotopes are planned.