Modeling microalgal abundance with artificial neural networks: Demonstration of a heuristic 'Grey-Box' to deconvolve and quantify environmental influences

An artificial neural network (ANN)-based technology - a 'Grey-Box', originating the iterative selection, depiction, and quantitation of environmental relationships for modeling microalgal abundance, as chlorophyll (CHL) a, was developed and evaluated. Due to their robust capability for reproducing the complexities underlying chaotic, non-linear systems, ANNs have become popular for the modeling of ecosystem structure and function. However, ANNs exhibit a holistic deficiency in declarative knowledge structure (i.e. a 'black-box'). The architecture of the Grey-Box provided the benefit of the ANN modeling structure, while deconvolving the interaction of prediction potentials among environmental variables upon CHL a. The influences of (pairs of) predictors upon the variance and magnitude of CHL a were depicted via pedagogical knowledge extraction (multi-dimensional response surfaces). This afforded derivation of mathematical equations for iterative predictive outcomes of CHL a and together with an algorithmic expression across iterations, corrected for the lack of declarative knowledge within conventional ANNs. Importantly, the Grey-Box 'bridged the gap' between 'white-box' parametric models and black-box ANNs in terms of performance and mathematical transparency. Grey-Box formulations are relevant to ecological niche modeling, identification of biotic response(s) to stress/disturbance thresholds, and qualitative/quantitative derivation of biota-environmental relationships for incorporation within stand-alone mechanistic models projecting ecological structure.

[1]  Kenneth H. Reckhow,et al.  Statistical Evaluation of Mechanistic Water‐Quality Models , 1990 .

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

[3]  J. J. Moré,et al.  Levenberg--Marquardt algorithm: implementation and theory , 1977 .

[4]  G. Weckman,et al.  MODELING PHYTOPLANKTON ABUNDANCE IN SAGINAW BAY, LAKE HURON: USING ARTIFICIAL NEURAL NETWORKS TO DISCERN FUNCTIONAL INFLUENCE OF ENVIRONMENTAL VARIABLES AND RELEVANCE TO A GREAT LAKES OBSERVING SYSTEM 1 , 2006 .

[5]  Mark E. Borsuk,et al.  Comparison of Estuarine Water Quality Models for Total Maximum Daily Load Development in Neuse River Estuary , 2003 .

[6]  S. Wood.  Statistical inference for noisy nonlinear ecological dynamic systems , 2010, Nature.

[7]  Zhenming Su,et al.  Quantitative Identification of Disturbance Thresholds in Support of Aquatic Resource Management , 2008, Environmental management.

[8]  Friedrich Recknagel,et al.  Elucidation and short-term forecasting of microcystin concentrations in Lake Suwa (Japan) by means of artificial neural networks and evolutionary algorithms. , 2007, Water research.

[9]  Friedrich Recknagel.  Ecological informatics: A discipline in the making , 2011, Ecol. Informatics.

[10]  Michele Scardi,et al.  Advances in neural network modeling of phytoplankton primary production , 2001 .

[11]  A. Peterson,et al.  PREDICTING SPECIES' GEOGRAPHIC DISTRIBUTIONS BASED ON ECOLOGICAL NICHE MODELING , 2001 .

[12]  Anne Johannet,et al.  Neural Networks: From Black Box towards Transparent Box Application to Evapotranspiration Modeling , 2008 .

[13]  Friedrich Recknagel,et al.  Prediction and Elucidation of Population Dynamics of the Blue-green Algae Microcystis aeruginosa and the Diatom Stephanodiscus hantzschii in the Nakdong River-Reservoir System (South Korea) by a Recurrent Artificial Neural Network , 2006 .

[14]  Boris Kompare,et al.  Environmental Modelling & Software , 2014 .

[15]  Silvia González,et al.  Neural Networks for Macroeconomic Forecasting : A Complementary Approach to Linear Regression Models , 2000 .

[16]  Hans W. Paerl,et al.  Using microalgal indicators to assess human- and climate-induced ecological change in estuaries , 2004 .

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

[18]  Orlando Sarnelle,et al.  Nutrient Enrichment and Grazer Effects on Phytoplankton in Lakes , 1992 .

[19]  Emilio Fernández,et al.  Modelling primary production in a coastal embayment affected by upwelling using dynamic ecosystem models and artificial neural networks , 1999 .

[20]  Richard R. Rediske,et al.  Late-summer phytoplankton in western Lake Erie (Laurentian Great Lakes): bloom distributions, toxicity, and environmental influences , 2009, Aquatic Ecology.

[21]  J. Rohr,et al.  Community responses to contaminants: Using basic ecological principles to predict ecotoxicological effects , 2009, Environmental toxicology and chemistry.

[22]  Gary R. Weckman,et al.  Using a heuristic approach to derive a grey-box model through an artificial neural network knowledge extraction technique , 2010, Neural Computing and Applications.

[23]  Mark V. Hoyer,et al.  Evaluation of recent limnological changes at Lake Apopka , 2001, Hydrobiologia.

[24]  Philip E. Gill,et al.  Practical optimization , 1981 .

[25]  Jason W. Osbourne,et al.  Four Assumptions of Multiple Regression That Researchers Should Always Test. , 2002 .

[26]  L. A. Bull,et al.  Relations between trophic state indicators and fish in Florida (U.S.A.) lakes , 1996 .

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

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

[29]  A. Peterson.  Uses and requirements of ecological niche models and related distributional models , 2006 .

[30]  Michele Scardi,et al.  Developing an empirical model of phytoplankton primary production: a neural network case study , 1999 .

[31]  A. Townsend Peterson,et al.  Ecological niche modeling as a new paradigm for large-scale investigations of diversity and distribution of birds , 2005 .

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

[33]  Walter K. Dodds,et al.  Nitrogen and phosphorus relationships to benthic algal biomass in temperate streams , 2002 .

[34]  Jenq-Neng Hwang,et al.  Introduction to Neural Networks for Signal Processing , 2001, Handbook of Neural Network Signal Processing.

[35]  Matthew B Jones,et al.  Ecoinformatics: supporting ecology as a data-intensive science. , 2012, Trends in ecology & evolution.

[36]  V. Kvasnicka,et al.  Neural and Adaptive Systems: Fundamentals Through Simulations , 2001, IEEE Trans. Neural Networks.

[37]  Helge Malmgren.  Artificial Neural Networks in Medicine and Biology. A philosophical introduction , 2000 .

[38]  Gary R. Weckman,et al.  Knowledge Extraction from the Neural ‘Black Box’ in Ecological Monitoring , 2009 .

[39]  Hans W. Paerl,et al.  Ecosystem Responses to Internal and Watershed Organic Matter Loading: Consequences for Hypoxia in the Eutrophying Neuse River Estuary, North Carolina, USA , 1998 .

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

[41]  S. Soyupak,et al.  Case studies on the use of neural networks in eutrophication modeling , 2000 .

[42]  Vitor Vasconcelos,et al.  Time Series Forecasting of Cyanobacteria Blooms in the Crestuma Reservoir (Douro River, Portugal) Using Artificial Neural Networks , 2006, Environmental management.

[43]  H. Paerl.  Nuisance phytoplankton blooms in coastal, estuarine, and inland waters1 , 1988 .

[44]  Jose C. Principe,et al.  Neural and adaptive systems : fundamentals through simulations , 2000 .

[45]  Gary R Weckman,et al.  AN “ENVIRO‐INFORMATIC” ASSESSMENT OF SAGINAW BAY (LAKE HURON, USA) PHYTOPLANKTON: DATA‐DRIVEN CHARACTERIZATION AND MODELING OF MICROCYSTIS (CYANOPHYTA) 1 , 2011, Journal of phycology.

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

[47]  J. Oksanen,et al.  Continuum theory revisited: what shape are species responses along ecological gradients? , 2002 .

[48]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[49]  Pejman Rohani,et al.  The colour of noise in short ecological time series data. , 2004, Mathematical medicine and biology : a journal of the IMA.

[50]  G Sugihara,et al.  Distinguishing error from chaos in ecological time series. , 1990, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[51]  Gérard Dreyfus,et al.  How to be a gray box: dynamic semi-physical modeling , 2001, Neural Networks.

[52]  K. Jeong,et al.  Non-linear autoregressive modelling by Temporal Recurrent Neural Networks for the prediction of freshwater phytoplankton dynamics , 2008 .

[53]  Kazumi Saito,et al.  Extracting regression rules from neural networks , 2002, Neural Networks.

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

[55]  Antony Browne,et al.  Knowledge extraction from neural networks , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[56]  Holger R. Maier,et al.  Use of artificial neural networks for modelling cyanobacteria Anabaena spp. in the River Murray, South Australia , 1998 .

[57]  H. Carrick,et al.  NICHE MODELING AND PREDICTIONS OF ALGAL BLOOMS IN AQUATIC ECOSYSTEMS , 2011, Journal of phycology.

[58]  Daming Shi,et al.  Sensitivity Analysis for Neural Networks , 2009, Sensitivity Analysis for Neural Networks.

[59]  Stefano Tarantola,et al.  Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models , 2004 .

[60]  Ronald J. Ryel,et al.  How much variance is explained by ecologists? Additional perspectives , 2003, Oecologia.

[61]  Yan Huang,et al.  Neural network modelling of coastal algal blooms , 2003 .

[62]  Selcuk Soyupak,et al.  Predicting dominant phytoplankton quantities in a reservoir by using neural networks , 2003, Hydrobiologia.

[63]  R. King,et al.  A new method for detecting and interpreting biodiversity and ecological community thresholds , 2010 .

[64]  Gary R. Weckman,et al.  Neural net modeling of estuarine indicators: Hindcasting phytoplankton biomass and net ecosystem production in the Neuse (North Carolina) and Trout (Florida) Rivers, USA , 2006 .

[65]  John A. Harrison,et al.  Escalating Worldwide use of Urea – A Global Change Contributing to Coastal Eutrophication , 2006 .

[66]  A. Cattaneo,et al.  Periphyton in Lakes of Different Trophy , 1987 .

[67]  David F. Millie,et al.  Intra-annual variability of water quality and phytoplankton in the North Fork of the St. Lucie River Estuary, Florida (USA): a quantitative assessment , 2004 .

[68]  M. Conner,et al.  Methods to quantify variable importance: implications for the analysis of noisy ecological data. , 2009, Ecology.

[69]  J. Osborne.  Notes on the use of data transformations. , 2002 .

[70]  Leon S. Lasdon,et al.  Design and Testing of a Generalized Reduced Gradient Code for Nonlinear Programming , 1978, TOMS.

[71]  Jason M Evans,et al.  Algal blooms and the nitrogen-enrichment hypothesis in Florida springs: evidence, alternatives, and adaptive management. , 2010, Ecological applications : a publication of the Ecological Society of America.