Temporal transferability of marine distribution models in a multispecies context

Abstract Transferability of species distribution models is crucial for supporting biological conservation and management planning in the face of climate changes; however, there is a lack of understanding in how to achieve transference spatially and temporally, especially in a multispecies circumstance. This study evaluated the roles of model complexity and time scope in temporal transferability for multispecies distribution modelling. We collected data of multispecies distribution from a seven-year marine survey in coastal Yellow Sea, China, and used the data to evaluate the predictive performances of an array of multi-species distribution models (constrained linear ordination, constrained additive ordination, hierarchical models of species communities, multivariate random forests, multivariate tree boosting model, and multivariate artificial neural network), characterized by different structures, levels of complexity and time spans with 36 models and 50 scenarios. Our study showed that model transference was proper for some species but limited at the community level in general, and no specific modelling algorithm (regression models/machine-learning) or level of model complexity was found to be superior. Instead, model structure, features of target species, and time scope contributed substantially and influenced transferability in a contingent way. Temporal transferability tended to increase with the length of training periods and decay with the time gaps of prediction, whereas the magnitude varied among modelling algorithms. In addition, prolonging the time series of survey programs alone may have limited effectiveness on community-level transferability. This study contributes to the understanding of temporal transferability of multi-species distribution models and inform their applications in biological conservation and management from a temporal perspective.

[1]  R. Julliard,et al.  REVIEW: Predictive ecology in a changing world , 2015 .

[2]  Rubén G. Mateo,et al.  Impact of model complexity on cross-temporal transferability in Maxent species distribution models: An assessment using paleobotanical data , 2015 .

[3]  Robert P. Anderson,et al.  The challenge of modeling niches and distributions for data‐poor species: a comprehensive approach to model complexity , 2018 .

[4]  Binduo Xu,et al.  Comparing the prediction of joint species distribution models with respect to characteristics of sampling data , 2018 .

[5]  Timothy G. Howard,et al.  Development and Delivery of Species Distribution Models to Inform Decision-Making , 2019, BioScience.

[6]  R. Gregory,et al.  Improving species distribution models: the value of data on abundance , 2014 .

[7]  C. Clark.  Modelling the behaviour of fishers and fishes , 2018 .

[8]  K. Fausch,et al.  Probabilistic accounting of uncertainty in forecasts of species distributions under climate change , 2013, Global change biology.

[9]  Paul L. Angermeier,et al.  Factors influencing behavior and transferability of habitat models for a benthic stream fish , 1997 .

[10]  A. Fielding,et al.  Testing the Generality of Bird‐Habitat Models , 1995 .

[11]  J. Olden.  A Species‐Specific Approach to Modeling Biological Communities and Its Potential for Conservation , 2003 .

[12]  M. Kearney,et al.  Correlation and process in species distribution models: bridging a dichotomy , 2012 .

[13]  Kerrie Mengersen,et al.  Transferring biodiversity models for conservation: Opportunities and challenges , 2018 .

[14]  Jane Elith,et al.  What do we gain from simplicity versus complexity in species distribution models , 2014 .

[15]  Anna Norberg,et al.  How to make more out of community data? A conceptual framework and its implementation as models and software. , 2017, Ecology letters.

[16]  Yiping Ren,et al.  Spatio-seasonal patterns of fish diversity, Haizhou Bay, China , 2014, Chinese Journal of Oceanology and Limnology.

[17]  Emiliano A. Valdez,et al.  Predictive analytics of insurance claims using multivariate decision trees , 2018, Dependence Modeling.

[18]  J. Elith,et al.  Species Distribution Models: Ecological Explanation and Prediction Across Space and Time , 2009 .

[19]  H. Van Dyck,et al.  Transferability of Species Distribution Models: a Functional Habitat Approach for Two Regionally Threatened Butterflies , 2007, Conservation biology : the journal of the Society for Conservation Biology.

[20]  Jari Oksanen,et al.  Joint species distribution modelling with the r‐package Hmsc , 2020, Methods in ecology and evolution.

[21]  Antoine Guisan,et al.  Spatial modelling of biodiversity at the community level , 2006 .

[22]  Trevor J Hastie,et al.  Reduced-rank vector generalized linear models , 2003 .

[23]  R. Real,et al.  A practical overview of transferability in species distribution modeling , 2017 .

[24]  Owen L. Petchey,et al.  The ecological forecast horizon, and examples of its uses and determinants , 2015, bioRxiv.

[25]  J. Bedia,et al.  A framework for species distribution modelling with improved pseudo-absence generation , 2015 .

[26]  P. Leadley,et al.  Impacts of climate change on the future of biodiversity. , 2012, Ecology letters.

[27]  Myrna E. Watanabe.  The Nagoya Protocol: The Conundrum of Defining Digital Sequence Information , 2019, BioScience.

[28]  Thomas W. Yee,et al.  A NEW TECHNIQUE FOR MAXIMUM‐LIKELIHOOD CANONICAL GAUSSIAN ORDINATION , 2004 .

[29]  L. A. Barnett,et al.  Comparing estimates of abundance trends and distribution shifts using single- and multispecies models of fishes and biogenic habitat , 2017 .

[30]  A. Peterson,et al.  An evaluation of transferability of ecological niche models , 2018, Ecography.

[31]  C. Dormann,et al.  Components of uncertainty in species distribution analysis: a case study of the Great Grey Shrike. , 2008, Ecology.

[32]  N. Isaac,et al.  Measuring β‐diversity with species abundance data , 2015, The Journal of animal ecology.

[33]  David B. Dunson,et al.  A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels , 2019, Ecological Monographs.

[34]  Mathieu Marmion,et al.  Does the interpolation accuracy of species distribution models come at the expense of transferability , 2012 .

[35]  J. Blois,et al.  Multiresponse algorithms for community‐level modelling: Review of theory, applications, and comparison to species distribution models , 2017 .

[36]  Thomas W Yee,et al.  Constrained additive ordination. , 2006, Ecology.

[37]  Antoine Guisan,et al.  Measuring the relative effect of factors affecting species distribution model predictions , 2014 .

[38]  David B. Roy,et al.  Uncovering hidden spatial structure in species communities with spatially explicit joint species distribution models , 2016 .

[39]  Brendan A. Wintle,et al.  Is my species distribution model fit for purpose? Matching data and models to applications , 2015 .

[40]  Yong Chen,et al.  Evolution of marine fisheries management in China from 1949 to 2019: How did China get here and where does China go next? , 2020 .

[41]  Ranadip Pal,et al.  IntegratedMRF: random forest‐based framework for integrating prediction from different data types , 2017, Bioinform..

[42]  P. I. Miller,et al.  Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds , 2012 .

[43]  Damaris Zurell,et al.  Outstanding Challenges in the Transferability of Ecological Models. , 2018, Trends in ecology & evolution.

[44]  D. Dunson,et al.  Sparse Bayesian infinite factor models. , 2011, Biometrika.

[45]  Mark R. Segal,et al.  Multivariate random forests , 2011, WIREs Data Mining Knowl. Discov..

[46]  Gitta H. Lubke,et al.  Finding structure in data using multivariate tree boosting , 2015, Psychological methods.

[47]  M. Araújo,et al.  Uses and misuses of bioclimatic envelope modeling. , 2012, Ecology.

[48]  S. Ferrier,et al.  Controlled comparison of species- and community-level models across novel climates and communities , 2016, Proceedings of the Royal Society B: Biological Sciences.

[49]  A. Peterson,et al.  Major challenges for correlational ecological niche model projections to future climate conditions , 2018, Annals of the New York Academy of Sciences.

[50]  Francis K. C. Hui,et al.  So Many Variables: Joint Modeling in Community Ecology. , 2015, Trends in ecology & evolution.

[51]  B. McGill,et al.  Testing the predictive performance of distribution models , 2013 .

[52]  M. Austin.  Spatial prediction of species distribution: an interface between ecological theory and statistical modelling , 2002 .

[53]  W. Thuiller,et al.  Predicting species distribution: offering more than simple habitat models. , 2005, Ecology letters.

[54]  Thomas A. Groen,et al.  Transferability of species distribution models: The case of Phytophthora cinnamomi in Southwest Spain and Southwest Australia , 2016 .

[55]  Julian D Olden,et al.  Rediscovering the species in community-wide predictive modeling. , 2006, Ecological applications : a publication of the Ecological Society of America.

[56]  Araceli Puente,et al.  Temporal transferability of marine distribution models: The role of algorithm selection , 2019, Ecological Indicators.

[57]  Julian D. Olden,et al.  Assessing transferability of ecological models: an underappreciated aspect of statistical validation , 2012 .

[58]  M. Julian Caley,et al.  Transferability of predictive models of coral reef fish species richness , 2016 .

[59]  D. Dunson,et al.  Using joint species distribution models for evaluating how species‐to‐species associations depend on the environmental context , 2017 .

[60]  Brian J. McGill,et al.  The priority of prediction in ecological understanding , 2017 .

[61]  Michael A. McCarthy,et al.  A comparison of joint species distribution models for presence–absence data , 2018, Methods in Ecology and Evolution.