Aedes aegypti (Linnaeus) (Diptera: Culicidae) is the principal tropical mosquito vector of arboviruses causing yellow fever, dengue and chikungunya [1]–[3]. The related Aedes albopictus Skuse is a secondary vector of dengue and chikungunya [1]–[4]. Unlike Ae. aegypti, Ae. albopictus possesses a diapausing egg stage to survive winters which has enabled it to spread to temperate regions and cause a chikungunya epidemic in northern Italy in 2007 [4].

Dengue is the most common arboviral disease of humans, with 50 million annual cases in more than 100 countries, an increasing incidence and spread worldwide, and 2.5 billion people at risk [5], [6]. About 500,000 persons require hospitalization every year for dengue hemorrhagic fever (DHF) and 2.5% of DHF cases are fatal [6]. Dengue is endemic in Sri Lanka with a high incidence in the northern and eastern districts of Jaffna and Batticaloa respectively [7]. Sri Lanka moreover experienced an epidemic of chikungunya in 2006–2007 [8]. Dengue is also endemic in Brunei and many other Southeast Asian countries [5], [9], [10]. There is presently no licensed vaccine or specific anti-viral drug for dengue [6], [9].Yellow fever, another flaviviral disease, is endemic in Africa and South America, has a zoonotic reservoir and is responsible for 200,000 cases and 30,000 deaths worldwide [11]. An effective vaccine is available against yellow fever, but it can potentially spread to Asia through increased global transport. Chikungunya, caused by an alphavirus, is endemic in Southeast Asia and has produced recent epidemics in Africa and South Asia [1], [2], [12]. Additional arboviral diseases with animal reservoirs are emerging as serious threats to human health [1], [13].

Ae. aegypti and Ae. albopictus have adapted to feed on humans and undergo larval and pupal development in natural ( e.g. rock pools, tree holes, leaf axils) and artificial (e.g. water tanks, blocked drains, decorative pots and discarded tyres and food/beverage containers) freshwater collections in the urban and peri-urban environment [1], [3], [5]. Ae. aegypti and Ae. albopictus are common anthropophagic mosquitoes in urban areas of Sri Lanka [14], [15]. Control of dengue and chikungunya in tropical countries is mainly achieved through surveillance for Ae. aegypti and Ae. albopictus larvae and eliminating larval development habitats, with the attendant use of insecticides and public education [5], [9], [10]. Larval control efforts invariably focus on freshwater development habitats of the two mosquito species near human habitations [5], [9], [10]. We investigated a hypothesis that Ae. aegypti and Ae. albopictus also undergo preimaginal development in brackish water in the peri-urban environment (water with <0.5 ppt or parts per thousand, 0.5–30 ppt and >30 ppt salt are termed fresh, brackish and saline respectively), with the potential thereby to make a hitherto unrecognized contribution to the transmission of dengue, chikungunya and other arboviral diseases.

The salinity tolerance of Ae. aegypti and Ae. albopictus larvae originating from Thirunelvely and Batticaloa town in the districts of Jaffna and Batticaloa respectively in Sri Lanka (Figure 1) were initially determined in the laboratory. The results are presented graphically in Figure 2 with relevant parameters tabulated in Table 1. The results show that, in all instances where 95% confidence intervals could be determined for the LC₅₀ values, the third instar larvae of both species were significantly more tolerant of salinity at p<0.05 , based on non-overlapping confidence intervals, than the corresponding first instar larvae at both locations (Table 1). These findings were confirmed by LC₅₀ ratio tests [17] at the p<0.01 level of significance (Table S1). The non-overlapping 95% confidence intervals (Table 1), confirmed by LC₅₀ ratio tests at p<0.01 (Table S1), also suggest that Aedes populations in Thirunelvely may be more tolerant of salinity than the corresponding ones from Batticaloa, with the caveat that the experimental comparison was done at different times in two separate laboratories, albeit under similar assay conditions. Ae. albopictus larvae also tended to have higher LC₅₀ values than the corresponding Ae. aegypti larvae at both locations but the differences were not statistically significant by either the 95% confidence interval (Table 1) or LC₅₀ ratio (Table S1) tests.

The capacity of the two Aedes species to lay eggs in field ovitraps containing water with salinity varying from 0 to 20 ppt was also determined. Observations were made weekly for six weeks in Thirunelvely. Ae. aegypti and Ae. albopictus laid significant numbers of eggs in ovitraps with salinity up to 18 ppt and 16 ppt respectively (Table 2). The analysis of variance showed that the multiple regression analysis model was highly significant (F = 13.9, df = 3, p<0.001) with partial regression coefficients demonstrating that this was due to the numbers of larvae collected per week increasing over time (coefficient = 0.17, T = 2.4, p = 0.016) and decreasing with increasing salinity in the ovitraps (coefficient = −0.77, T = −5.8, p<0.001). However the multiple regression analysis showed that the numbers of larvae collected per week were not significantly different between the two mosquito species (coefficient = −2.49, T = −1.5, p = 0.145).

Potential brackish water preimaginal development sites of Ae. aegypti and Ae. albopictus in the coastal peri-urban environment of Thannamunai, Batticaloa district were then investigated over a four month period. Among 83 discarded food and beverage containers with brackish water that were inspected 14 (17%), with salinity levels ranging from 2 to 14 ppt, were found to contain either Ae. aegypti or Ae. albopictus larvae (Table 3). The salinity of water samples from containers that did not possess Aedes larvae varied from 2 to16 ppt. Of 89 potential brackish water habitats subsequently investigated along the coast of Jaffna city, three disused boats and two abandoned wells (6%) were found to contain Ae. aegypti larvae in a salinity range 3 to15 ppt (Table 3, with illustrative photographs of habitats in Figure 3). The salinity of brackish water samples from habitats in Jaffna city that did not contain Aedes larvae varied from 1–18 ppt. Along the main road from the Jaffna coast to Thirunelvely, 102 frequently used domestic wells were also examined. Aedes larvae were not found in such wells, where the salinities ranged from 9 ppt near the sea to 0 ppt in Thirunelvely (Figure 4).

The incidence of dengue in the period 1 October 2010 to 30 April 2011 in Jaffna city, which included the larval survey period of February and March 2011, was relatively high in divisions close to the coastal brackish water sites where Ae. aegypti larvae were detected (Figure 5).

Several mosquito species with salinity-tolerant larvae are vectors of human arboviral and parasitic diseases in many parts of the world [18]. They include some members of the genus Aedes, e.g. Aedes togoi Theobald found in coastal marshes and Aedes taeniorhyncus Wiedemann in splash pools, whose osmoregulatory mechanisms have been well studied [19]. Ae. aegypti and Ae. albopictus in contrast have been widely regarded to undergo preimaginal development only in freshwater [3], [5]. However early laboratory studies showed that Ae. aegypti larvae can tolerate limited salinity changes through an osmoconformation mechanism involving the accumulation of amino acids and ions in the haemolymph [20]. Our findings show that Ae. aegypti and Ae. albopictus can oviposit and undergo preimaginal development in fresh (tap) and brackish waters under field conditions, but that oviposition diminishes with increasing salinity of the water. Previous laboratory studies of oviposition by established laboratory colonies of Ae. aegypti showed that it prefers 2.5 ppt salinity compared to distilled water for oviposition [21], [22]. These studies also suggested that Ae. aegypti can oviposit in up to 30 ppt salinity under laboratory conditions. However such findings may not be directly applicable to the natural situation where freshwater habitats would contain dissolved minerals that might influence oviposition. They are also not directly comparable to our data with field mosquito populations and tap water from an artesian well source that contains dissolved minerals. A study on the oviposition preference of a laboratory colony of Ae. albopictus found that tap water was preferred to 1 ppt and higher concentrations of NaCl [23]. Our data from Thirunelvely suggest that Ae. aegypti and Ae. albopictus are able to oviposit in a field situation over a relatively wide range of salinity of up to 18 ppt and 16 ppt respectively. This is consistent with the finding of their larvae in brackish water collections of 2 to 15 ppt salinity in Thannamunai and Jaffna city coasts. In the context of the findings in Thirunelvely, it may be relevant to compare the salinity tolerance of the larvae of mosquitoes emerging from fresh and brackish water ovitraps as this can demonstrate potential genetic differences in the field populations of mosquitoes. Water conditioned by previous culture with Ae. albopictus larvae enhances oviposition by Ae. albopictus [23], presumably due to the presence of chemicals that are sensed by receptors in the gravid female mosquito [22]. This phenomenon could explain the greater oviposition with time in the field ovitraps observed in our investigation. However an increase in mosquito abundance could have also caused or contributed to the increasing oviposition during the six week study period.

Ae. aegypti larvae derived from an established laboratory colony showed approximately 80% survival in deionized water, >90% survival at 3.5 ppt salinity, rapid decrease in survival at >8 ppt salinity with an approximate LC₅₀ of 14 ppt, and 0% survival at 17.5 ppt salinity in a study by Clarke et al. in the United States [24]. This study further showed that preimaginal development times were prolonged and pupal mass reduced at high salinities [24]. Because of the use of deionized water as the control and for diluting sea water, a different criterion for survival, and the use of larvae from an established laboratory colony in that study, the results are not strictly comparable to our present findings. However, the LC₅₀ values for the two Aedes species for both first and third instar larvae in Batticaloa tend to be lower and the LC₅₀ values for Thirunelvely similar to the LC₅₀ observed with the Ae. aegypti laboratory colony by Clarke et al. [24]. The greater salinity tolerance of third instar larvae compared to first instar larvae observed in our study may be due to structural and physiological changes related to those that reduce ion permeability in pupae [19].

The Jaffna peninsula in Sri Lanka, unlike Batticaloa, is largely composed of sedimentary limestone and has many lagoons and other inland saline water bodies. Groundwater from aquifers and wells is over-used for domestic and agricultural purposes and therefore groundwater salinization, as illustrated also in Figure 4 for domestic wells, is widespread [25]. This effect is compounded by a high population density of approximately 700 persons per km² in the 1130 km² peninsula. Although Thirunelvely is an area where the accessible ground water in wells is fresh (Figure 4), the small size of the Jaffna peninsula provides many areas with brackish water close enough to Thirunelvely to be within reach of Aedes populations. The possibly greater salinity tolerance of the Aedes populations in Thirunelvely compared to Batticaloa needs to be confirmed by parallel experiments carried out under identical conditions in the same laboratory but may reflect adaptive genetic differences in the two populations analogous to that seen in Aedes camptorhynchus Thomson, a salinity-tolerant vector of Ross River virus in Southwestern Australia [26]. Larvae of coastal marsh populations of Ae. camptorhynchus tolerate greater salinity (52 ppt, i.e. hypersalinity) than inland populations (30 ppt, i.e. approaching the average salinity of sea water), probably due to genetic changes in osmoregulatory mechanisms [26]. The gradual adaptation of laboratory colonies of Ae. taeniorhyncus to increasing salinity are also likely to be due to genetic changes [19]. Genetic adaptation of mosquitoes to tolerate salinity in preimaginal habitats is also exemplified by differential salinity tolerance among sibling species of Anopheles mosquitoes [18].

Ae. aegypti and Ae. albopictus, are widely adapted to urban and suburban environments in Sri Lanka [27], Brunei [9] and many other countries [1], [10]. Although Ae. albopictus is reportedly more exophillic than Ae. aegypti, both mosquitoes normally lay eggs within a 1 km radius of their feeding site, thereby ensuring continuing proximity to human hosts [28]. This facilitates the human-mosquito-human transmission cycle which is normal for urban dengue and chikungunya, and during epidemics of yellow fever in urban areas [1]. However sylvatic cycles continue to exist in some regions for yellow fever and chikungunya [1]. Our findings now show that Ae. aegypti and Ae. albopictus lay eggs and their larvae and pupae survive to emerge as adults in brackish water, and that brackish water habitats with larvae are present in the peri-urban environment in Sri Lanka. The brackish water larval sites identified in this study are located in popular beaches or coastal areas <1 km from densely populated housing, consistent with their potential role in dengue and chikungunya transmission. These findings are compatible with oviposition by the two Aedes species in brackish water observed in a field situation, and the extent of salinity tolerance shown by their larvae in laboratory studies. Larval indices like the premises index (PI, the percentage of houses with freshwater containers positive for larvae) are commonly used entomological parameters for assessing the potential for the transmission of dengue by Ae. aegypti and Ae. albopictus [5], [10]. Dengue outbreaks have occurred in areas with a PI of approximately 2% in Singapore [10] and Cuba [29]. The relevance of 6% and 17% larval positivity rates for brackish water collections in Sri Lanka, although a different measure from the PI, needs to be evaluated further in the context of their potential contribution to the transmission of dengue and chikungunya. The present findings are also consistent with the possibility that sites where larvae of Ae. aegypti were found in brackish water may be located in the vicinity of neighborhoods with a higher dengue incidence in the coastal areas of Jaffna city, Sri Lanka. Ae. albopictus larvae were also found in brackish water within discarded food and beverage containers, with salinities up to 8 ppt, along the urban coast of dengue-endemic Brunei (R.R., S.N.S., Idris, F., Yasin, K.M., unpublished data), suggesting that our findings in Sri Lanka may be applicable to many other countries. Detailed epidemiological studies are however needed to conclusively demonstrate that preimaginal development of the two Aedes species in brackish water contributes to the transmission of dengue, chikungunya and other arboviral diseases.

It is possible that adaptation of the two Aedes populations to salinity may be accompanied by alterations in their vectorial capacity and this merits further investigation. The viability of the preimaginal stages, preimaginal development times and fitness of the emergent adults in brackish water habitats in the environment also need to be determined. Our results further suggest that brackish and freshwater domestic wells that are in frequent use are not common habitats for the preimaginal development of the two Aedes species, possibly because of regular disturbance of the water surface and rapid water turnover as well as a paucity of decaying organic matter that provide oviposition cues [30].

Small tropical islands and Southeast Asian countries have a high coastline to land mass ratio and therefore proportionately more potential coastal brackish water sites where the two Aedes species may undergo preimaginal development. Because of the exclusive focus of larval control measures on freshwater habitats [5], [10], [27], it is possible that Aedes vectors undergoing preimaginal development in brackish water collections in artificial containers have unknowingly contributed to the persistence or emergence of dengue and chikungunya in Sri Lanka [7], [8], chikungunya in Reunion [31], and dengue, despite intensive control programs, in countries like Cuba [32], Singapore [10] and Brunei [9]. High and increasing population densities in coastal areas with attendant socio-economic changes [18] and failing refuse collection systems may exacerbate this situation in resource-poor countries. Salinity-tolerant Ae. albopictus will further increase the potential for transmission of dengue and chikungunya in temperate zone countries.

Climate (temperature, rainfall, humidity) change due to global warming can expand the geographical range of vector mosquitoes, extend the disease transmission season, shorten the gonotrophic cycle and reduce the time taken for ingested viruses to develop to infectivity in mosquitoes, thereby increasing the propagation rates of arboviral diseases by Ae. aegypti and Ae. albopictus [1], [2], [4], [33]–[35]. Furthermore, a rise in sea levels consequent to global warming can increase the extent of natural brackish surface water bodies in coastal areas [36], an effect that can be compounded by higher rates of withdrawal of water from freshwater aquifers in coastal areas by expanding populations [37]. A hypothesis, presented in detail elsewhere [18], suggests that rising sea levels can therefore increase the abundance of salinity-tolerant mosquito vectors and lead to the adaptation of normally freshwater vectors to brackish waters, thereby additionally enhancing transmission of mosquito-borne diseases in coastal areas. The predicted increase in the worldwide population density of coastal areas from 87 persons per km² in the year 2000 to 134 persons per km² in 2050 [38] is also likely to exacerbate the situation by increasing human-vector contact.

Our results show that Ae. aegypti and Ae. albopictus have successfully adapted to oviposit and undergo preimaginal development in brackish water collections in unused wells and discarded artificial containers of up to 15 ppt salinity in the peri-urban environment. Similar salinity levels occur in parts of natural brackish water bodies like lagoons, estuaries, coastal marshes and tidal pools, as well as ponds, lakes and wells near urbanized coasts. There is no evidence at present for the large scale adaptation of Ae. aegypti and Ae. albopictus to undergo preimaginal development in natural brackish or saline water bodies. Continuous application of vector control methods solely to freshwater preimaginal development habitats in the urban environment may select for genetic changes favoring the development of Ae. aegypti and Ae. albopictus in artificial collections of brackish water in coastal urban areas, which in turn, could conceivably also lead to their adaptation to natural brackish water habitats in the future. Such changes could have serious consequences for the health of millions of people in many parts of the world, through a higher incidence of dengue, chikungunya and urban yellow fever as well as other rarer arboviral diseases [1], [4], [13]. The presence of Ae. aegypti larvae in disused brackish water wells in Jaffna and the possibly greater salinity tolerance of both Ae. aegypti and Ae. albopictus larvae in the Jaffna peninsula, where there is more salinization of groundwater compared to Batticaloa [25], may herald the beginning of this adaptive process. We recently showed that Anopheles culicifacies Giles, the major vector of malaria in Sri Lanka and an established freshwater species [39], is able to undergo preimaginal development in brackish waters of salinity up to 4 ppt in Sri Lanka [40]. Additionally Anopheles subpictus Grassi species B with genetic similarity to Anopheles sundaicus Rodenwaldt was demonstrated to be an euryhaline species (ability to tolerate a range of salinities) in Sri Lanka with its larvae being isolated from freshwater and 30 ppt salinity water in a lagoon [41]. Our present findings suggest Ae. aegypti and Ae. albopictus may have also developed euryhaline-like features, and that further investigations are required to characterize possible genetic changes that may be responsible. National and international health authorities however need to recognize the potential impact on human health of brackish water-adapted Ae. aegypti, Ae. albopictus and other mosquito vectors that were traditionally considered to be freshwater species, and institute appropriate surveillance and control measures.