The deep learning (DL) revolution is touching all scientific disciplines and corners of our lives as a means of harnessing the power of big data. Marine ecology is no exception. New methods provide analysis of data from sensors, cameras, and acoustic recorders, even in real time, in ways that are reproducible and rapid. Off-the-shelf algorithms find, count, and classify species from digital images or video and detect cryptic patterns in noisy data. These endeavours require collaboration across ecological and data science disciplines, which can be challenging to initiate. To promote the use of DL towards ecosystem-based management of the sea, this paper aims to bridge the gap between marine ecologists and computer scientists. We provide insight into popular DL approaches for ecological data analysis, focusing on supervised learning techniques with deep neural networks, and illustrate challenges and opportunities through established and emerging applications of DL to marine ecology. We present case studies on plankton, fish, marine mammals, pollution, and nutrient cycling that involve object detection, classification, tracking, and segmentation of visualized data. We conclude with a broad outlook of the field’s opportunities and challenges, including potential technological advances and issues with managing complex data sets.
Wrasse (Labridae) fisheries have increased markedly in Norway since 2010. Wrasse are being used as cleaner fish in salmonid aquaculture to control sea-lice infestations. However, fundamental knowledge on the demography and abundance of the targeted wrasse populations in Norwegian waters is lacking, and the consequences of harvesting at the current intensity have not been assessed. Here, we compared catch per unit effort (CPUE), size, age and sex ratio of goldsinny wrasse (Ctenolabrus rupestris) and corkwing wrasse (Symphodus melops) between marine protected areas (MPAs) and control areas open for fishing at four localities on the Skagerrak coast in Southern Norway. The CPUE of goldsinny larger than the minimum size limit was 33–65% higher within MPAs, while for corkwing three of four MPAs had higher CPUE with the relative difference between MPAs and control areas ranging from −16% to 92%. Moreover, corkwing, but not goldsinny, was significantly older and larger within MPAs than in control areas. Sex ratios did not differ between MPAs and control areas for either species. Our study suggests that despite its short history, the wrasse fisheries have considerable impacts on the target populations and, further, that small MPAs hold promise as a management tool for maintaining natural population sizes and size structure. Goldsinny, being a smaller-sized species, also seems to benefit from the traditional minimum size limit management tool, which applies outside MPAs.
Size selective harvesting can also be selective on sex in species displaying sexual size dimorphism (SSD). This has potential consequences for mating systems and population dynamics. Here, we assessed spatial variation in SSD and body size in eight Norwegian populations of corkwing wrasse (Symphodus melops), a species where males either mature as nesting or sneaker males. Corkwing wrasse is increasingly harvested in a size-selective fishery which supplies the Norwegian salmon aquaculture industry with cleaner fish to reduce sea-lice infestations. In our study, mature nesting males had larger body sizes than females and sneaker males, and the size difference was significantly larger in the four northernmost populations. Contrasting life history traits in two of the populations (a southern and a northern), we found that the larger SSD in the north was because of nesting males delaying maturation and growing faster relative to females and sneaker males. Mature northern nesting males also had smaller gonads at smaller sizes relative to their southern counterparts, indicating a trade-off between reproduction and somatic growth in males. Applying the current minimum legal size limit for commercial fishing in Norway (12 cm) would have failed to protect any mature nesting males in five out of the eight populations. Moreover, the findings of more male-biased SSD and female-biased sex ratios in the northern populations imply that there is larger potential for sex-selective harvesting in these populations. To avoid fisheries-induced changes in sex ratios, we advocate for spatially structured management units and to refine the current size-regulations using either sex-specific minimum size limits or a slot limit, also protecting the larger fish and therefore more nesting males.
Removing individuals from a wild population can affect the availability of prospective mates and the outcome of competitive interactions, with subsequent effects on mating patterns and sexual selection. Consequently, the rate of harvest‐induced evolution is predicted to be strongly dependent on the strength and dynamics of sexual selection, yet there is limited empirical knowledge on the interplay between selective harvesting and the mating systems of exploited species. In this study, we used genetic parentage assignment to compare mating patterns of the highly valued and overexploited European lobster (Homarus gammarus) in a designated lobster reserve and nearby fished area in southern Norway. In the area open to fishing, the fishery is regulated by a closed season, a minimum legal size and a ban on the harvest of egg‐bearing females. Due to the differences in size and sex‐specific fishing mortality between the two areas, males and females are of approximately equal average size in the fished area, whereas males tend to be larger in the reserve. Our results show that females would mate with males larger than their own body size, but the relative size difference was significantly larger in the reserve. Sexual selection acted positively on both body size and claw size in males in the reserve, while it was nonsignificant in fished areas. This strongly suggests that size truncation of males by fishing reduces the variability of traits that sexual selection acts upon. If fisheries continue to target large individuals (particularly males) with higher relative reproductive success, the weakening of sexual selection will likely accelerate fisheries‐induced evolution towards smaller body size.
16 December 2016 in ICES Journal of Marine Science
Fishery-induced changes in sex ratios can have negative effects on reproductive rates and affect sexual selection and evolutionary trajectories. Here, we investigate sex- and size-selectivity of the fishery for corkwing wrasse (Symphodus melops) in Western Norway. The males that build and guard nests (nesting males) grow faster than females and sneaker males. Corkwing wrasse were tagged (n = 1057) during (May–June) and after (July) the spawning period in 2014 within a no-take site and in a nearby site open for fishing. We monitored the fishery within and nearby the tagging sites from June to October and sampled recaptures on all commercial fishing trips. Fishing mortality was higher for nesting males than for females (open site; tagged during spawning: 36% vs. 29%; after spawning: 49% vs. 36%) and was found to be caused by nesting males having higher capture probabilities than females, independently of body size. The fishing mortality of sneaker males did not differ from nesting males, but the sample of sneaker males in the study was small. The probability of being retained by fishers once captured depended on size, but not on sex. The small no-take site reduced fishing mortality, and the sex- and size-selectivity was similar to the open site. By demonstrating the capture process to be male-selective in a commercial fishery, our study highlights the importance of assessing sex-selectivity in similar fisheries. If detected, management measures protecting the sexes more equally should be implemented, such as slot-size limits and marine-protected areas large enough to account for sexual differences in spatial behaviour.