Unexpected high losses of Anopheles gambiae larvae due to rainfall

Abstract

Background: Immature stages of the malaria mosquito Anopheles gambiae experience high mortality, but its cause is poorly understood. Here we study the impact of rainfall, one of the abiotic factors to which the immatures are frequently exposed, on their mortality.

Methodology/principal findings: We show that rainfall significantly affected larval mosquitoes by flushing them out of their aquatic habitat and killing them. Outdoor experiments under natural conditions in Kenya revealed that the additional nightly loss of larvae caused by rainfall was on average 17.5% for the youngest (L1) larvae and 4.8% for the oldest (L4) larvae; an additional 10.5% (increase from 0.9 to 11.4%) of the L1 larvae and 3.3% (from 0.1 to 3.4%) of the L4 larvae were flushed away and larval mortality increased by 6.9% (from 4.6 to 11.5%) and 1.5% (from 4.1 to 5.6%) for L1 and L4 larvae, respectively, compared to nights without rain. On rainy nights, 1.3% and 0.7% of L1 and L4 larvae, respectively, were lost due to ejection from the breeding site.

Conclusions/significance: This study demonstrates that immature populations of malaria mosquitoes suffer high losses during rainfall events. As these populations are likely to experience several rain showers during their lifespan, rainfall will have a profound effect on the productivity of mosquito breeding sites and, as a result, on the transmission of malaria. These findings are discussed in the light of malaria risk and changing rainfall patterns in response to climate change.

Figure 1. Rainfall during the study period.

Total rainfall quantity, including maximum rainfall intensity (in grey), per night from April 10 (Day Of Year 100) up to July 27 (DOY 208). The arrows indicate missing data. Note that DOY 141 up to 167 are omitted from the figure, as no experiments were carried out.

Figure 2. Losses of Anopheles gambiae larvae during nights with and without rainfall.

Percentages of L1 and L4 larvae of An. gambiae that were flushed away or died and the overall loss during nights without rainfall (on the left) and nights with rainfall (on the right). The asterisks (***) indicate the level of significance between L1 and L4 larvae (p<0.001). The error bars indicate the standard error of the mean.

Figure 3. Experimental setup.

(A), Schematic side view of flush/survival experiment. (B), Schematic side view of ejecting-experiment. The solid lines represent the basins; the dotted lines the thin tripod metal frames. The openings in the basins are the overflow holes screened with mesh-wire; the black crosses indicate where the larvae were placed at the start of each experiment.