Sexual selection results in differential reproductive success among individuals of the same sex [1]. Usually, males have a higher potential reproductive rate than females, and are thus most often the competing sex, while females are the more choosy sex (reviewed in [2]). Recent studies have shown that both the intensity of mating competition and the potential benefits for females of mating with certain males can be influenced by several extrinsic factors, such that behavioral decisions can be highly context-dependent (e.g. [3]–[6]).

Animals that expend their entire reproductive effort over the course of a single season provide a distinctive opportunity to study context-sensitive mating decisions. In this study, we examined mate choice in the annual killifish Austrolebias reicherti (Teleostei: Rivulidae). These fish live in temporary ponds that dry out completely during the dry summer months; lifespan is restricted by the duration of the pond, usually between 4 and 6 months [7]. Austrolebias, along with some other cyprinodontiform fishes, deposit desiccation-resistant eggs in the substrate of the temporary ponds they inhabit [8]. Developing embryos can undergo reversible diapauses until environmental conditions for egg eclosion become suitable [9]–[10], allowing them to survive long periods of desiccation. Individuals then hatch, mature, reproduce, and die within the span of a very short season. They therefore complete their life cycle in <1 year, with no overlapping generations.

Austrolebias are highly sexually dimorphic: males are larger, exhibit bright coloration, perform elaborate courtship displays, and compete for mating; while females are smaller, relatively cryptic, and do not court [11]–[12]. Female Austrolebias prefer to mate with larger males [13]. There are two, perhaps mutually reinforcing reasons why we might expect this preference to decline over the course of a breeding season. First, as the end of the season approaches, any benefits of choosiness are presumably reduced: a female’s fitness will be higher if she mates with any male than if she forgoes reproduction and dies. Second, females should become less choosy as the operational sex ratio (OSR) becomes increasingly female-skewed. Adult males are likely to suffer higher mortality due to exhaustion resulting from social interactions [14]–[15], a higher susceptibility to parasites and diseases [14]–[16], and increased predation risk [17]–[18]. The OSR is therefore likely to become increasingly female-biased over the course of a season. Female choosiness should be lower under a female-biased OSR than a male-biased OSR because of the increased costs of mate rejection [19]–[20]. Decreased intersexual encounter rates also mean that females may be less able to assess male phenotypic variation [21]. Indeed, several experimental studies have found that manipulating the OSR induces changes in mating preferences in the predicted direction (e.g. [22]–[26]), and field studies have shown that the strength of female mate choice covaries with population OSR (e.g. [27]).

We predicted both a decrease in the availability of male A. reicherti over the course of the reproductive season, and a decrease in female preference for large body size. In this study, we measured the sex ratio in multiple wild populations, and assayed female mating decisions at the beginning and at the end of the reproductive season.

We found seasonal change in both operational sex ratio and female mate choice in the annual killifish Austrolebias reicherti. At the beginning of the reproductive season (August) the OSR did not deviate from parity, and females preferred larger males. Later in the reproductive season (October–November), the OSR became female-biased and females became unselective with respect to male size.

These results are consistent with previous findings showing that female choosiness decreases under female-biased OSR [22]–[27]. Declines in the number of males, leading to female-biased sex ratios late in the breeding season, have been reported in other fish (e.g. [5]), including annual killifish in the genus Nothobranchius [35]. We have not observed any sex differences in mortality rate or biases in the adult sex ratio in the laboratory, suggesting that increased extrinsic mortality in males could lead to the observed biases in the OSR at the end of the season in natural populations. Austrolebias species exhibit both intense male–male competition, often involving serious injuries to subordinate males, and elaborate male courtship displays during reproduction [13], [28]. A plausible explanation is that high male mortality stems from exhaustion resulting from courtship displays or male-male competition [14]–[15]. Further, males exhibit bright coloration and showy sexual displays that may incur increased predation risk [17], [36].

At the start of the reproductive season, larger males were strongly preferred, and the strength of female preference was positively related with the size difference between stimulus males. Preference exhibited by female A. reicherti towards larger males is consistent with female choice based on male body size, which is widespread in cyprinodontiform fishes [37]–[39]. Passos et al. [13] previously reported that females preferred larger males in A. charrua.

However, female preference for larger males vanished at the end of the reproductive season. Females were equally likely to choose small or large males later in the season and female preference was not affected by the size difference between stimulus males. It is important to note that male size distributions, and the mean differences between tested males, did not change over the course of the breeding season. The observed change in preference for body size is therefore the result of changes in female choosiness rather than the distribution of available males.

Reduction in choosiness could arise from diminished reproductive prospects due to a decline in male availability [40]–[41]. As the sex ratio becomes female biased late in the season, the opportunity for female choice may be reduced by a decline in rate of encounters with males [42], an increase in female-female competition, and/or because males may become more selective in their mating decisions [5]. Further, approaching mortality may cause time constraints on female mate searching [43]–[44]. As this critical time approaches, a female may be faced with a trade-off in which she will have to decrease choosiness or risk losing the opportunity to fertilize her eggs. In this regard, the particular biological cycle of annual killifish, where both life expectancy and mating opportunities decline over time, could account for the seasonal change in female choice.

Although we have shown that female preference for body size is reduced over the course of the season, it is not necessarily the case that female A. reicherti become entirely non-selective. In fact, neither the difference in the time females spent with each male nor the total interaction time with both males were significantly different at the beginning and end of the reproductive season. Then, the observed seasonal variation in female choice may be due to shifts in the weights that females assign to different male traits [3]. The fitness consequences for females of mating with certain males may vary throughout the season, and females might then be expected to change how they respond to multiple male cues as environmental conditions or individual phenotypes change (e.g. [45]–[46]). Larger males have a competitive advantage with respect to male-male competition [13] and females could obtain direct benefits from mating with them early season to gain access to preferred areas for oviposition. However, the advantages of male size and the benefits to females of choosing large males may be reduced late in the season because lower male density may decrease the intensity of male-male competition. These reduced direct benefits are a potential driver of the lack of preference for male size at the end of the reproductive season. Therefore, female choice in A. reicherti could be based on other cues if traits other than male size become relatively more important for female reproductive success later in the reproductive season. Females do not attend to variation in male pigmentation (unpublished data), but Passos et al. [47] showed that female A. reicherti respond to the chemical cues of potential mates. The habitat of annual fish such as A. reicherti consists mostly of shallow ponds with muddy substrate, turbid water and high vegetation density, which could hinder the use of vision particularly near the end of a season. The extremely variable habitat provided by temporary ponds exposes A. reicherti to drastic environmental changes, and the use of different sensory modalities could vary over the life cycle (see [48]–[49]). Future studies will address whether sensitivity to chemical cues changes over the course of a season.

In summary, we have shown seasonal changes in both operational sex ratios, and mating preferences for male body size in the annual killifish A. reicherti. Female preference for larger males disappeared with the decline of male availability over the season and as the window of opportunity for future reproduction became narrower. Future work will address whether females attend to different male traits over the course of a season, and disentangle the mechanisms leading to female behavioral changes, notably direct responses to demographic factors, environmental cues, or intrinsic changes during senescence.