Assessing the Role of Environmental Factors on Baltic Cod Recruitment, a Complex Adaptive System Emergent Property

For decades, fish recruitment has been a subject of intensive research with stock–recruitment models commonly used for recruitment prediction often only explaining a small fraction of the inter-annual recruitment variation. The use of environmental information to improve our ability to predict recruitment, could contribute considerably to fisheries management. However, the problem remains difficult because the mechanisms behind such complex relationships are often poorly understood; this in turn, makes it difficult to determine the forecast estimation robustness, leading to the failure of some relationships when new data become available. The utility of machine learning algorithms such as artificial neural networks (ANNs) for solving complex problems has been demonstrated in aquatic studies and has led many researchers to advocate ANNs as an attractive, non-linear alternative to traditional statistical methods. The goal of this study is to design a Baltic cod recruitment model (FishANN) that can account for complex ecosystem interactions. To this end, we (1) build a quantitative model representation of the conceptual understanding of the complex ecosystem interactions driving Baltic cod recruitment dynamics, and (2) apply the model to strengthen the current capability to project future changes in Baltic cod recruitment. FishANN is demonstrated to bring multiple stressors together into one model framework and estimate the relative importance of these stressors while interpreting the complex nonlinear interactions between them. Additional requirements to further improve the current study in the future are also proposed.

[1]  C. Möllmann,et al.  Effects of climate and overfishing on zooplankton dynamics and ecosystem structure: regime shifts, trophic cascade, and feedback loops in a simple ecosystem , 2008 .

[2]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[3]  Berkeley,et al.  Critical transitions in nature and society , 2009, Choice Reviews Online.

[4]  M. Murray A review and comparison , 2008 .

[5]  Soung Hie Kim,et al.  An Artificial Neural Network Approach , 1993 .

[6]  W. Ricker Stock and Recruitment , 1954 .

[7]  Ding-Geng Chen,et al.  A neural network model for forecasting fish stock recruitment , 1999 .

[8]  Christian Möllmann,et al.  Beauty is in the eye of the beholder: Management of Baltic cod stock requires an ecosystem approach , 2011 .

[9]  J. Sjöberg Non-Linear System Identification with Neural Networks , 1995 .

[10]  Ding-Geng Chen,et al.  A fuzzy logic model with genetic algorithm for analyzing fish stock-recruitment relationships , 2000 .

[11]  Julian D Olden,et al.  Assessing ecosystem vulnerability to invasive rusty crayfish (Orconectes rusticus). , 2011, Ecological applications : a publication of the Ecological Society of America.

[12]  George Sugihara,et al.  Detecting and forecasting complex nonlinear dynamics in spatially structured catch-per-unit- effort time series for North Pacific albacore (Thunnus alalunga) , 2011 .

[13]  Donald A. Jackson,et al.  Fish–Habitat Relationships in Lakes: Gaining Predictive and Explanatory Insight by Using Artificial Neural Networks , 2001 .

[14]  Hone-Jay Chu,et al.  Modeling waterbird diversity in irrigation ponds of Taoyuan, Taiwan using an artificial neural network approach , 2009, Paddy and Water Environment.

[15]  Gabriel Navarro,et al.  A Bayesian model for anchovy (Engraulis encrasicolus): the combined forcing of man and environment , 2009 .

[16]  C. Möllmann,et al.  Reorganization of a large marine ecosystem due to atmospheric and anthropogenic pressure: a discontinuous regime shift in the Central Baltic Sea , 2009 .

[17]  Klaus-Robert Müller,et al.  Asymptotic statistical theory of overtraining and cross-validation , 1997, IEEE Trans. Neural Networks.

[18]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[19]  Shijie Zhou Application of Artificial Neural Networks for Forecasting Salmon Escapement , 2003 .

[20]  Ding-Geng Chen,et al.  Recruitment prediction with genetic algorithms with application to the Pacific Herring fishery , 2007 .

[21]  Michael Obach,et al.  Artificial neural nets and abundance prediction of aquatic insects in small streams , 2006, Ecol. Informatics.

[22]  B. MacKenzie,et al.  Recruitment of Baltic cod and sprat stocks: identification of critical life stages and incorporation of environmental variability into stock-recruitment relationships* , 2003 .

[23]  Jarno Vanhatalo,et al.  General state-space population dynamics model for Bayesian stock assessment , 2015 .

[24]  Michel Dreyfus-León,et al.  Recruitment prediction for Pacific herring (Clupea pallasi) on the west coast of Vancouver Island, Canada , 2008, Ecol. Informatics.

[25]  Iñaki Inza,et al.  Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species , 2015, Ecol. Informatics.

[26]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[27]  Antoni Quetglas,et al.  The Use of Artificial Neural Networks (ANNs) in Aquatic Ecology , 2011 .

[28]  Yannis Dimopoulos,et al.  Use of some sensitivity criteria for choosing networks with good generalization ability , 1995, Neural Processing Letters.

[29]  Michael J. Watts,et al.  Using artificial neural networks to determine the relative contribution of abiotic factors influencing the establishment of insect pest species , 2008, Ecol. Informatics.

[30]  S. Levin Self-organization and the Emergence of Complexity in Ecological Systems , 2005 .

[31]  S. Levin,et al.  Resilience, Robustness, and Marine Ecosystem-based Management , 2008 .

[32]  D. H. Cushing,et al.  The Dependence of Recruitment on Parent Stock in Different Groups of Fishes , 1971 .

[33]  F. Burden,et al.  A quantitative structure--activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. , 2000, Chemical research in toxicology.

[34]  Frank Hansen,et al.  An approach for determining relative input parameter importance and significance in artificial neural networks , 2007 .

[35]  Sovan Lek,et al.  Modelling of microhabitat used by fish in natural and regulated flows in the river Garonne (France) , 2001 .

[36]  Thorsten Blenckner,et al.  Impact of Climate Change on Fish Population Dynamics in the Baltic Sea: A Dynamical Downscaling Investigation , 2012, AMBIO.

[37]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[38]  Thomas J. Miller,et al.  Contribution of individual-based coupled physical-biological models to understanding recruitment in marine fish populations , 2007 .

[39]  Steven R. Hare,et al.  Neural network and fuzzy logic models for pacific halibut recruitment analysis , 2006 .

[40]  Thomas Brey,et al.  Artificial neural network versus multiple linear regression: predicting P/B ratios from empirical data , 1996 .

[41]  N. Stenseth,et al.  Ecological forecasting under climate change: the case of Baltic cod , 2010, Proceedings of the Royal Society B: Biological Sciences.

[42]  J. J. Colbert,et al.  Interannual changes in sablefish (Anoplopoma fimbria) recruitment in relation to oceanographic conditions within the California Current System , 2006 .

[43]  Kamil A. Bekiashev,et al.  International Council for the Exploration of the Sea (ICES) , 1981 .

[44]  Michele Gristina,et al.  SMART: A Spatially Explicit Bio-Economic Model for Assessing and Managing Demersal Fisheries, with an Application to Italian Trawlers in the Strait of Sicily , 2014, PloS one.

[45]  Lin Sun,et al.  Forecasting Fish Stock Recruitment and Planning Optimal Harvesting Strategies by Using Neural Network , 2009, J. Comput..

[46]  Andreas Fischer,et al.  How to determine the unique contributions of input-variables to the nonlinear regression function of a multilayer perceptron , 2015 .

[47]  Sovan Lek,et al.  Improved estimation, using neural networks, of the food consumption of fish populations , 1995 .

[48]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[49]  Beatriz A. Roel,et al.  Potential improvements in the management of Bay of Biscay anchovy by incorporating environmental indices as recruitment predictors , 2005 .

[50]  Laura Uusitalo,et al.  Advantages and challenges of Bayesian networks in environmental modelling , 2007 .

[51]  Friedrich Recknagel,et al.  Ecological Informatics: Scope, Techniques and Applications , 2006 .

[52]  Iñaki Inza,et al.  Supervised pre-processing approaches in multiple class variables classification for fish recruitment forecasting , 2013, Environ. Model. Softw..

[53]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[54]  Young-Seuk Park,et al.  Modelling the factors that influence fish guilds composition using a back-propagation network: Assessment of metrics for indices of biotic integrity , 2003 .

[55]  Juan de Oña,et al.  Extracting the contribution of independent variables in neural network models: a new approach to handle instability , 2014, Neural Computing and Applications.

[56]  Julian D Olden,et al.  Machine Learning Methods Without Tears: A Primer for Ecologists , 2008, The Quarterly Review of Biology.

[57]  E. Houde,et al.  Emerging from Hjort's Shadow , 2008 .

[58]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[59]  Morten Vinther,et al.  Why is the Eastern Baltic cod recovering , 2012 .

[60]  F. Burden,et al.  Robust QSAR models using Bayesian regularized neural networks. , 1999, Journal of medicinal chemistry.

[61]  Sovan Lek,et al.  Predicting fish yield of african lakes using neural networks , 1999 .

[62]  Study on the Medium and Long Term of Fishery Forecasting Based on Neural Network , 2012, AICI.

[63]  M. Tomczak,et al.  Climate influence on Baltic cod, sprat, and herring stock–recruitment relationships , 2010 .

[64]  B. MacKenzie,et al.  Developing Baltic cod recruitment models. II. Incorporation of environmental variability and species interaction , 2001 .

[65]  R. Death,et al.  Predictive modelling and spatial mapping of freshwater fish and decapod assemblages using GIS and neural networks , 2004 .

[66]  H. Nakata Towards a Science of Recruitment in Fish Populations , 1998 .

[67]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[68]  Graham Nuthall,et al.  Illuminating the black box , 2006, Nature.

[69]  Hans-Harald Hinrichsen,et al.  Stock recruitment relationships for cod ( Gadus morhua L.) in the central Baltic Sea incorporating environmental variability , 2000 .

[70]  Nils Chr. Stenseth,et al.  Recruitment of walleye pollock in a physically and biologically complex ecosystem: A new perspective , 2005 .

[71]  Costas Papaconstantinou,et al.  Predicting demersal fish species distributions in the Mediterranean Sea using artificial neural networks , 2003 .

[72]  M. Gevrey,et al.  Two-way interaction of input variables in the sensitivity analysis of neural network models , 2006 .

[73]  Nedyalko Petrov,et al.  Deriving margins in prostate cancer radiotherapy treatment: comparison of neural network and fuzzy logic models , 2012, Int. J. Bioinform. Res. Appl..

[74]  Sovan Lek,et al.  Stochastic models that predict trout population density or biomass on a mesohabitat scale , 1996, Hydrobiologia.

[75]  Stefano Cataudella,et al.  When behaviour reveals activity: Assigning fishing effort to métiers based on VMS data using artificial neural networks , 2011 .

[76]  B. MacKenzie,et al.  Baltic cod recruitment – the impact of climate variability on key processes , 2005 .

[77]  H. Sparholt Causal correlation between recruitment and spawning stock size of central Baltic cod , 1996 .

[78]  Ross Nelson,et al.  Predicting Ecologically Important Vegetation Variables from Remotely Sensed Optical/Radar Data Using Neural Networks , 2000 .

[79]  C. Möllmann,et al.  Trophodynamic control by clupeid predators on recruitment success in Baltic cod , 2000 .

[80]  K. Wieland,et al.  Prediction of vertical distribution and ambient development temperature of Baltic cod, Gadus morhua L., eggs , 1997 .

[81]  B. Planque,et al.  Non-Deterministic Modelling of Food-Web Dynamics , 2014, PloS one.

[82]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[83]  Archontoula Chaloulakou,et al.  Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens. , 2003, The Science of the total environment.

[84]  Jose A. Lozano,et al.  Fish recruitment prediction, using robust supervised classification methods , 2010 .

[85]  O. Heikinheimo Average salinity as an index for environmental forcing on cod recruitment in the Baltic Sea , 2008 .

[86]  J. Raga,et al.  Parasite infracommunities as predictors of harvest location of bogue (Boops boops L.): a pilot study using statistical classifiers , 2005 .

[87]  A. Konstantinos,et al.  A Comparative Assessment , 2003 .

[88]  M. Cardinale,et al.  Trophic cascades promote threshold-like shifts in pelagic marine ecosystems , 2009, Proceedings of the National Academy of Sciences.

[89]  Teruhisa Komatsu,et al.  Prediction of the Catch of Japanese Sardine Larvae in Sagami Bay Using a Neural Network , 1994 .

[90]  Benjamin Planque,et al.  Quantile regression models for fish recruitment-environment relationships : four case studies , 2008 .

[91]  Julian D. Olden,et al.  An artificial neural network approach for studying phytoplankton succession , 2000, Hydrobiologia.

[92]  I. Dimopoulos,et al.  Application of neural networks to modelling nonlinear relationships in ecology , 1996 .

[93]  I. Dimopoulos,et al.  Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece) , 1999 .

[94]  G. N. Rao,et al.  Neural networks in fisheries research , 2008 .

[95]  R. Tol,et al.  Testing the implications of a permanent or seasonal marine reserve on the population dynamics of Eastern Baltic cod under varying environmental conditions , 2007 .

[96]  Young-Seuk Park,et al.  Modelling Community Structure in Freshwater Ecosystems , 2014 .

[97]  Geir Huse,et al.  Capelin migrations and climate change – a modelling analysis , 2008 .

[98]  Ian T. Carroll,et al.  Understanding and predicting ecological dynamics: are major surprises inevitable? , 2008, Ecology.

[99]  S. Lek,et al.  The use of artificial neural networks to predict the presence of small‐bodied fish in a river , 1997 .

[100]  S. Liong,et al.  GENERALIZATION FOR MULTILAYER NEURAL NETWORK BAYESIAN REGULARIZATION OR EARLY STOPPING , 2004 .

[101]  F. Recknagel,et al.  Artificial neural network approach for modelling and prediction of algal blooms , 1997 .

[102]  Jan Horbowy,et al.  Incorporating environmental variability in stock assessment: predicting recruitment, spawner biomass, and landings of sprat (Sprattus sprattus) in the Baltic Sea , 2008 .

[103]  K. Hüssy,et al.  Eastern Baltic cod in distress biological changes and challenges for stock assessment , 2015 .

[104]  Brian J. Rothschild,et al.  ''Fish stocks and recruitment'': the past thirty years , 2000 .

[105]  Uygar Özesmi,et al.  An artificial neural network approach to spatial habitat modelling with interspecific interaction , 1999 .

[106]  R. Beverton,et al.  On the dynamics of exploited fish populations , 1993, Reviews in Fish Biology and Fisheries.