Morand et al. (2024) designed convolutional neural networks to predict the occurrences of 38 marine animals worldwide. The environmental predictors were sea surface temperature, chlorophyll concentration, salinity and fifteen others. The time of some of the predictors was chosen to be as close as possible to the time of the observed occurrence.

This approach has previously only been applied to the analysis of the distribution of terrestrial plant species (Botella et al. 2018, Deneu et al. 2021), so the application here to very different marine ecosystems and organisms is a novelty worth highlighting and discussing.

A very interesting feature of PCI Ecology is that reviews are provided with the final manuscript and the present recommendation text.

In the case of the Morand et al. article, the reviewers provided very detailed and insightful comments that deserve to be published and read alongside the article.

The reviewers' comments question the ecological significance and implications of choosing fine temporal and spatial scales in CNN distribution modelling in order to obtain species distribution modelling (SDM).

The main question debated during the review process was whether the CNN modeling approach used here can be defined as a kind of niche modeling.

The fact is that most of the organisms studied here are mobile, and the authors have taken into account precise environmental information at dates close to those of species appearance (for example, "Temperature and chlorophyll values were also included 15 and 5 days before the occurrences"). In doing so, they took into account the fine spatial and temporal scales of species occurrences and environmental conditions, which can be influenced by both environmental preferences and the movement behaviors of individuals. The question then arises: does this approach really represent the ecological niches of the marine organisms selected? Given that most selected organisms may have specific seasonal movement dynamics, the CNN model also learns the individual movement behaviors of organisms over seasons and years. The ecological niche is a broader concept that takes into account all the environmental conditions that enable species to persist over the course of their lives and over generations. This differs from the case of sessile land plants, which must respond to the environmental context only at the points of appearance.

This is not a shortcoming of the methodology proposed here but rather an interesting conceptual issue to be considered and discussed. Modelling the occurrence of individuals at a given time and position can characterize not only the species' niche but also the dynamics of organisms' temporal movements. As a result, the model predicts the position of individuals at a given time, while the niche should also represent the role of environmental conditions faced by individuals at other times in their lives.
A relevant perspective would then be to analyze whether and how the neural network can help disentangle the ranges of environmental conditions defining the niche from those influencing the movement dynamics of individuals.

Another interesting point is that the CNN model is used here as a multi-species classifier, meaning that it provides the ranked probability that a given observation corresponds to one of the 38 species considered in the study, depending on the environmental conditions at the location and time of the observation. In other words, the model provides the relative chance of choosing each of the 38 species at a given time and place. Imagine that you are only studying two species that have exactly the same niche, a standard SDM approach should provide a high probability of occurrence close to 1 in localities where environmental conditions are very and equally suited to both species, while the CNN classifier would provide a value close to 0.5 for both species, meaning that we have an equal chance of choosing one or the other. Consequently, the fact that the probability given by the classifier is higher for a species at a given point than at another point does not (necessarily) mean that the first point presents better environmental conditions for that species but rather that we are more likely to choose it over one of the other species at this point than at another. In fact, the classification task also reflects whether the other 37 species are more or less likely to be found at each point. The classifier, therefore, does not provide the relative probability of occurrence of a species in space but rather a relative chance of finding it instead of one of the other 37 species at each point of space and time.

It is important that an ecologist designing a multi-species classifier for species distribution modelling is well aware of this point and does not interpret the variation of probabilities for a species in space as an indication of more or less suitable habitat for that specific species. On the other hand, predicting the relative probabilities of finding species to a given point at a given time gives an indication of the dynamics of their local co-occurrence. In this respect, the CNN approach is closer to a joint species distribution model (jSDM). As Ovaskainen et al. (2017) mention, "By simultaneously drawing on the information from multiple species, these (jSDM) models allow one to seek community-level patterns in how species respond to their environment". Let's return to the two species example we used above. The fact that the probabilities are 0.5 for both species actually suggests that both species can coexist at the same abundance at this location. In this respect, the CNN multi-species classifier offers promising prospects for the prediction of assemblages and habitats thanks to the relative importance of the most characteristic/dominant species from a species pool. The species pool comprises all classified species and must be sufficiently representative of the ecological diversity of species niches in the area.

Finally, CNN-based species distribution modelling is a powerful and promising tool for studying the distributions of multi-species assemblages as a function of local environmental features but also of the spatial heterogeneity of each feature around the observation point in space and time (Deneu et al. 2021). It allows acknowledging the complex effects of environmental predictors and the roles of their spatial and temporal heterogeneity through the convolution operations performed in the neural network. As more and more computationally intensive tools become available, and as more and more environmental data becomes available at finer and finer temporal and spatial scales, the CNN approach is likely to be increasingly used to study biodiversity patterns across spatial and temporal scales.

References

Botella, C., Joly, A., Bonnet, P., Monestiez, P., and Munoz, F. (2018). Species distribution modeling based on the automated identification of citizen observations. Applications in Plant Sciences, 6(2), e1029. https://doi.org/10.1002/aps3.1029

Deneu, B., Servajean, M., Bonnet, P., Botella, C., Munoz, F., and Joly, A. (2021). Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS Computational Biology, 17(4), e1008856. https://doi.org/10.1371/journal.pcbi.1008856

Morand, G., Joly, A., Rouyer, T., Lorieul, T., and Barde, J. (2024) Predicting species distributions in the open ocean with convolutional neural networks. bioRxiv, ver.3 peer-reviewed and recommended by PCI Ecology https://doi.org/10.1101/2023.08.11.551418

Ovaskainen, O., Tikhonov, G., Norberg, A., Guillaume Blanchet, F., Duan, L., Dunson, D., ... and Abrego, N. (2017). How to make more out of community data? A conceptual framework and its implementation as models and software. Ecology letters, 20(5), 561-576. https://doi.org/10.1111/ele.12757

In this paper, Alan R. Rogers (2021) examines the dynamics of foraging strategies for a resource that gains value over time (e.g., ripening fruits), while there is a fixed cost of attempting to forage the resource, and once the resource is harvested nothing is left for other harvesters. For this model, not any pure foraging strategy is evolutionary stable. A mixed equilibrium exists, i.e., with a mixture of foraging strategies within the population, which is still evolutionarily unstable. Nonetheless, Alan R. Rogers shows that for a large number of competitors and/or high harvesting cost, the mixture of strategies remains close to the mixed equilibrium when simulating the dynamics. Surprisingly, in a large population individuals will less often attempt to forage the resource and will instead “go fishing”. The paper also exposes an experiment of the game with students, which resulted in a strategy distribution somehow close to the theoretical mixture of strategies.

The economist John F. Nash Jr. (1950) gained the Nobel Prize of economy in 1994 for his game theoretical contributions. He gave his name to the “Nash equilibrium”, which represents a set of individual strategies that is reached whenever all the players have nothing to gain by changing their strategy while the strategies of others are unchanged. Alan R. Rogers shows that the mixed equilibrium in the foraging game is such a Nash equilibrium. Yet it is evolutionarily unstable insofar as a distribution close to the equilibrium can invade.

The insights of the study are twofold. First, it sheds light on the significance of Nash equilibrium in an ecological context of foraging strategies. Second, it shows that an evolutionarily unstable state can rule the composition of the ecological system. Therefore, the contribution made by the paper should be most significant to better understand the dynamics of competitive communities and their eco-evolutionary trajectories. 

References

Nash JF (1950) Equilibrium points in n-person games. Proceedings of the National Academy of Sciences, 36, 48–49. https://doi.org/10.1073/pnas.36.1.48

Rogers AR (2021) Beating your Neighbor to the Berry Patch. bioRxiv, 2020.11.12.380311, ver. 8 peer-reviewed and recommended by Peer Community in Ecology. https://doi.org/10.1101/2020.11.12.380311

Sexual segregation appears in many taxa and can have important ecological, evolutionary and conservation implications. Sexual segregation can take two forms: either the two sexes specialise in different habitats but share the same area (habitat segregation), or they occupy the same habitat but form separate, unisex groups (social segregation) [1,2]. Segregation would have evolved as a way to avoid, or at least, reduce intersexual competition.
Testing whether social or habitat segregation is at play necessitates the use of combined approaches to determine the spatial scale at which segregation occurs. This enterprise is even more challenging when studying marine species, which travel over long distances to reach their foraging areas. This is what Barbraud et al. [3] have endeavoured on the snow petrel (Pagodroma nivea), a sexually dimorphic, polar seabird. Studying sexual segregation at sea requires tools for indirect measures of habitat use and foraging tactics. During the incubation period, in a colony based at Pointe Geologie, Adelie land, East Antarctica, the team has equipped birds with GPS loggers to analyse habitat use and foraging behaviour. It has also compared short-, mid-, and long-term stable isotopic profiles, from plasma, blood cells, and feather samples, respectively.
Barbraud et al. [3] could not detect any evidence for sexual segregation in space use. Furthermore, the two sexes showed similar δ13C profiles, illustrating similar foraging latitudes, and indicating no sexual segregation at large spatial scales. Snow petrels all forage exclusively in the sea ice environment formed over the deep Antarctic continental shelf. The authors, however, found other forms of segregation: males consistently foraged at higher sea ice concentrations than females. Males also fed on higher trophic levels than females. Therefore, male and female snow petrels segregate at a smaller spatial scale, and use different foraging tactics and diet specialisations. Females also took shorter foraging trips than males, with higher mass gain that strongly benefit from higher sea ice concentration. Mass gain in males increased with the length of their foraging trip at sea ice areas.
The authors conclude that high sea ice concentration offers the most favourable foraging habitat for snow petrels, and thus that intersexual competition may drive females away from high sea ice areas. This study shows that combining information from different tools provides an elegant way of isolating the potential factors driving sexual segregation and the spatial scales at which it occurs.

References

[1] Conradt, L. (2005). Definitions, hypotheses, models and measures in the study of animal segregation. In Sexual segregation in vertebrates: ecology of the two sexes (Ruckstuhl K.E. and Neuhaus, P. eds). Cambridge University Press, Cambridge, United Kingdom. Pp:11–34.
[2] Ruckstuhl, K. E. (2007). Sexual segregation in vertebrates: proximate and ultimate causes. Integrative and Comparative Biology, 47(2), 245-257. doi: 10.1093/icb/icm030
[3] Barbraud, C., Delord, K., Kato, A., Bustamante, P., & Cherel, Y. (2018). Sexual segregation in a highly pagophilic and sexually dimorphic marine predator. bioRxiv, 472431, ver. 3 peer-reviewed and recommended bt PCI Ecology. doi: 10.1101/472431

Alarm calls are an important acoustic signal that can decide the life or death of an individual. Many birds are able to vary their alarm calls to provide more accurate information on e.g. urgency or even the type of a threatening predator. According to the acoustic adaptation hypothesis, the habitat plays an important role too in how acoustic patterns get transmitted. This is of particular interest for range-expanding species that will face new environmental conditions along the leading edge. One could hypothesize that the alarm call repertoire of a species could increase in newly founded ranges to incorporate new habitats and threats individuals might face. Hence selection for a larger active vocabulary might be beneficial for new colonizers. Using the Great-Tailed Grackle (Quiscalus mexicanus) as a model species, Samantha Bowser from Arizona State University and Maggie MacPherson from Louisiana State University want to find out exactly that. 

The Great-Tailed Grackle is an appropriate species given its high vocal diversity. Also, the species consists of different subspecies that show range expansions along the northern range edge yet to a varying degree. Using vocal experiments and field recordings the researchers have a high potential to understand more about the acoustic adaptation hypothesis within a range dynamic process. 

Over the course of this assessment, the authors incorporated the comments made by two reviewers into a strong revision of their research plans. With that being said, the few additional comments made by one of the initial reviewers round up the current stage this interesting research project is in. 

To this end, I can only fully recommend the revised research plan and am much looking forward to the outcomes from the author’s experiments, modeling, and field data. With the suggestions being made at such an early stage I firmly believe that the final outcome will be highly interesting not only to an ornithological readership but to every ecologist and biogeographer interested in drivers of range dynamic processes.

References

Bowser, S., MacPherson, M. (2021). A study on the role of social information sharing leading to range expansion in songbirds with large vocal repertoires: Enhancing our understanding of the Great-Tailed Grackle (Quiscalus mexicanus) alarm call. In principle recommendation by PCI Ecology. https://doi.org/10.17605/OSF.IO/2UFJ5. Version 3

Understanding why and how species coexist in local communities is one of the central questions in ecology. There is general agreement that species distribution and coexistence are determined by a number of key mechanisms, including the environmental requirements of species, dispersal, evolutionary constraints, resource availability and selection, metapopulation dynamics, and biotic interactions (e.g. Soberón & Nakamura 2009; Colwell & Rangel 2009; Ricklefs 2015). These factors are however intricately intertwined in a scale-structured fashion (Hortal et al. 2010; D’Amen et al. 2017), making it particularly difficult to tease apart the effects of each one of them. This could be addressed by the novel field of Joint Species Distribution Modelling (JSDM; Okasvainen & Abrego 2020), as it allows assessing the effects of several sets of factors and the co-occurrence and/or covariation in abundances of potentially interacting species at the same time (Pollock et al. 2014; Ovaskainen et al. 2016; Dormann et al. 2018). However, the development of JSDM has been hampered by the general lack of good-quality detailed data on species co-occurrences and abundances (see Hortal et al. 2015).

Facon et al. (2021) use a particularly large compilation of field surveys to study the abundance and co-occurrence of Tephritidae fruit flies in c. 400 orchards, gardens and natural areas throughout the island of Réunion. Further, they combine such information with lab data on their host-selection fundamental niche (i.e. in the absence of competitors), codifying traits of female choice and larval performances in 21 host species. They use Poisson Log-Normal models, a type of mixed model that allows one to jointly model the random effects associated with all species, and retrieve the covariations in abundance that are not explained by environmental conditions or differences in sampling effort. Then, they use a series of models to evaluate the effects on these matrices of ecological covariates (date, elevation, habitat, climate and host plant), species interactions (by comparing with a constrained residual variance-covariance matrix) and the species’ host-selection fundamental niches (through separate models for each fly species).

The eight Tephritidae species inhabiting Réunion include both generalists and specialists in Solanaceae and Cucurbitaceae with a known history of interspecific competition. Facon et al. (2021) use a comprehensive JSDM approach to assess the effects of different factors separately and altogether. This allows them to identify large effects of plant hosts and the fundamental host-selection niche on species co-occurrence, but also to show that ecological covariates and weak –though not negligible– species interactions are necessary to account for all residual variance in the matrix of joint species abundances per site. Further, they also find evidence that the fitness per host measured in the lab has a strong influence on the abundances in each host plant in the field for specialist species, but not for generalists. Indeed, the stronger effects of competitive exclusion were found in pairs of Cucurbitaceae specialist species. However, these analyses fail to provide solid grounds to assess why generalists are rarely found in Cucurbitaceae and Solanaceae. Although they argue that this may be due to Connell’s (1980) ghost of competition past (past competition that led to current niche differentiation), further data on the evolutionary history of these fruit flies is needed to assess this hypothesis.

Finding evidence for the effects of competitive interactions on species’ occurrences and spatial distributions is often difficult, perhaps because these effects occur over longer time scales than the ones usually studied by ecologists (Yackulic 2017). The work by Facon and colleagues shows that weak effects of competition can be detected also at the short ecological timescales that determine coexistence in local communities, under the virtuous combination of good-quality data and sound analytical designs that account for several aspects of species’ niches, their biotopes and their joint population responses. This adds a new dimension to the application of Hutchinson’s (1978) niche framework to understand the spatial dynamics of species and communities (see also Colwell & Rangel 2009), although further advances to incorporate dispersal-driven metacommunity dynamics (see, e.g., Ovaskainen et al. 2016; Leibold et al. 2017) are certainly needed. Nonetheless, this work shows the potential value of in-depth analyses of species coexistence based on combining good-quality field data with well-thought out JSDM applications. If many studies like this are conducted, it is likely that the uprising field of Joint Species Distribution Modelling will improve our understanding of the hierarchical relationships between the different factors affecting species coexistence in ecological communities in the near future.

References

Colwell RK, Rangel TF (2009) Hutchinson’s duality: The once and future niche. Proceedings of the National Academy of Sciences, 106, 19651–19658. https://doi.org/10.1073/pnas.0901650106

Connell JH (1980) Diversity and the Coevolution of Competitors, or the Ghost of Competition Past. Oikos, 35, 131–138. https://doi.org/10.2307/3544421

D’Amen M, Rahbek C, Zimmermann NE, Guisan A (2017) Spatial predictions at the community level: from current approaches to future frameworks. Biological Reviews, 92, 169–187. https://doi.org/10.1111/brv.12222

Dormann CF, Bobrowski M, Dehling DM, Harris DJ, Hartig F, Lischke H, Moretti MD, Pagel J, Pinkert S, Schleuning M, Schmidt SI, Sheppard CS, Steinbauer MJ, Zeuss D, Kraan C (2018) Biotic interactions in species distribution modelling: 10 questions to guide interpretation and avoid false conclusions. Global Ecology and Biogeography, 27, 1004–1016. https://doi.org/10.1111/geb.12759

Facon B, Hafsi A, Masselière MC de la, Robin S, Massol F, Dubart M, Chiquet J, Frago E, Chiroleu F, Duyck P-F, Ravigné V (2021) Joint species distributions reveal the combined effects of host plants, abiotic factors and species competition as drivers of community structure in fruit flies. bioRxiv, 2020.12.07.414326. ver. 4 peer-reviewed and recommended by Peer community in Ecology. https://doi.org/10.1101/2020.12.07.414326

Hortal J, de Bello F, Diniz-Filho JAF, Lewinsohn TM, Lobo JM, Ladle RJ (2015) Seven Shortfalls that Beset Large-Scale Knowledge of Biodiversity. Annual Review of Ecology, Evolution, and Systematics, 46, 523–549. https://doi.org/10.1146/annurev-ecolsys-112414-054400

Hortal J, Roura‐Pascual N, Sanders NJ, Rahbek C (2010) Understanding (insect) species distributions across spatial scales. Ecography, 33, 51–53. https://doi.org/10.1111/j.1600-0587.2009.06428.x

Hutchinson, G.E. (1978) An introduction to population biology. Yale University Press, New Haven, CT.

Leibold MA, Chase JM, Ernest SKM (2017) Community assembly and the functioning of ecosystems: how metacommunity processes alter ecosystems attributes. Ecology, 98, 909–919. https://doi.org/10.1002/ecy.1697

Ovaskainen O, Abrego N (2020) Joint Species Distribution Modelling: With Applications in R. Cambridge University Press, Cambridge. https://doi.org/10.1017/9781108591720

Ovaskainen O, Roy DB, Fox R, Anderson BJ (2016) Uncovering hidden spatial structure in species communities with spatially explicit joint species distribution models. Methods in Ecology and Evolution, 7, 428–436. https://doi.org/10.1111/2041-210X.12502

Pollock LJ, Tingley R, Morris WK, Golding N, O’Hara RB, Parris KM, Vesk PA, McCarthy MA (2014) Understanding co-occurrence by modelling species simultaneously with a Joint Species Distribution Model (JSDM). Methods in Ecology and Evolution, 5, 397–406. https://doi.org/10.1111/2041-210X.12180

Ricklefs RE (2015) Intrinsic dynamics of the regional community. Ecology Letters, 18, 497–503. https://doi.org/10.1111/ele.12431

Soberón J, Nakamura M (2009) Niches and distributional areas: Concepts, methods, and assumptions. Proceedings of the National Academy of Sciences, 106, 19644–19650. https://doi.org/10.1073/pnas.0901637106

Yackulic CB (2017) Competitive exclusion over broad spatial extents is a slow process: evidence and implications for species distribution modeling. Ecography, 40, 305–313. https://doi.org/10.1111/ecog.02836