Improvement of complex and refractory ecological models: Riverine water quality modelling using evolutionary computation

Abstract Complex environmental models have frequently suffered from large discrepancies between prediction and reality, inaccurate quantification of multivariate parameters, and difficulties in dealing with nonlinearities. We introduce an interdisciplinary project combining an ecological river-process model and evolutionary optimisation of model parameters, resulting in tools for more effective water resource management. The aim is to more tightly integrate the expert's knowledge and the evolutionary system through an iterated cycle of knowledge refinement and evolutionary search. This requires new methods to specify the expert knowledge in ways that can be integrated into the search. We used an evolutionary algorithm to optimise the multivariate values of the model parameters while retaining their acceptability, verifying that their ranges and values were consistent with ecological knowledge and constraints. The best model had a significantly lower predictive error than the initial process model parameterised from literature estimates. Its error was also over 50% less than those of the purely empirical modelling methods of linear regression and neural network learning. We conclude that combining process knowledge with evolutionary learning can play an important role in ecological modelling.

[1]  Peter A. Whigham,et al.  Winter diatom blooms in a regulated river in South Korea: explanations based on evolutionary computation , 2007 .

[2]  George B. Arhonditsis,et al.  Eutrophication model for Lake Washington (USA): Part I. Model description and sensitivity analysis , 2005 .

[3]  Nguyen Xuan Hoai,et al.  Evolutionary Operator Self-adaptation with Diverse Operators , 2012, EuroGP.

[4]  Gea-Jae Joo,et al.  Microcystis bloom formation in the lower Nakdong River, South Korea: importance of hydrodynamics and nutrient loading , 1999 .

[5]  P. Reichert,et al.  Analysis of the transferability of a biogeochemical lake model to lakes of different trophic state , 2006 .

[6]  Friedrich Recknagel,et al.  Process-based simulation library SALMO-OO for lake ecosystems. Part 2: Multi-objective parameter optimization by evolutionary algorithms , 2008, Ecol. Informatics.

[7]  K. Mcnyset,et al.  Use of ecological niche modelling to predict distributions of freshwater fish species in Kansas , 2005 .

[8]  E. Donk,et al.  TEMPERATURE EFFECTS ON SILICON‐ AND PHOSPHORUS‐LIMITED GROWTH AND COMPETITIVE INTERACTIONS AMONG THREE DIATOMS 1 , 1990 .

[9]  David E. Goldberg,et al.  Probability Matching, the Magnitude of Reinforcement, and Classifier System Bidding , 1990, Machine Learning.

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  Friedrich Recknagel,et al.  Applications of machine learning to ecological modelling , 2001 .

[12]  Seok Soon Park,et al.  A water quality modeling study of the Nakdong River, Korea , 2002 .

[13]  George B. Arhonditsis,et al.  Eutrophication model for Lake Washington (USA) Part II-model calibration and system dynamics analysis , 2005 .

[14]  Peter A. Whigham,et al.  Predicting chlorophyll-a in freshwater lakes by hybridising process-based models and genetic algorithms , 2001 .

[15]  A. Gelman.  Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper) , 2004 .

[16]  Peter A. Whigham,et al.  Modelling Microcystis aeruginosa bloom dynamics in the Nakdong River by means of evolutionary computation and statistical approach , 2003 .

[17]  S. Jung,et al.  Effects of temperature and nutrient depletion and reintroduction on growth of Stephanodiscus hantzschii (Bacillariophyceae): implications for the blooming mechanism , 2011 .

[18]  J. Bailey–Brock,et al.  An Unique Anchialine Pool in the Hawaiian Islands , 1998 .

[19]  David P. Hamilton,et al.  Challenges and opportunities for integrating lake ecosystem modelling approaches , 2010, Aquatic Ecology.

[20]  G. Joo,et al.  The longitudinal distribution and community dynamics of zooplankton in a regulated large river: a case study of the Nakdong River (Korea) , 2000, Hydrobiologia.

[21]  J. Descy,et al.  Potamon: a dynamic model for predicting phytoplankton composition and biomass in lowland rivers. , 2001, Water research.

[22]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[23]  C. Wellen,et al.  Application of the SPARROW model in watersheds with limited information: a Bayesian assessment of the model uncertainty and the value of additional monitoring , 2014 .

[24]  C. Reynolds.  The Ecology of Phytoplankton , 2006 .

[25]  Friedrich Recknagel,et al.  Predictive function and rules for population dynamics of Microcystis aeruginosa in the regulated Nakdong River (South Korea), discovered by evolutionary algorithms , 2007 .

[26]  Dirk Thierens,et al.  An Adaptive Pursuit Strategy for Allocating Operator Probabilities , 2005, BNAIC.

[27]  B. Moss,et al.  Ecology of fresh waters : man and medium, past to future , 1998 .

[28]  S. Chapra.  Surface Water-Quality Modeling , 1996 .

[29]  Peter A. Whigham,et al.  Comparative application of artificial neural networks and genetic algorithms for multivariate time-series modelling of algal blooms in freshwater lakes , 2002 .

[30]  Edward M. Buchak,et al.  CE-QUAL-W2: A Two-Dimensional, Laterally Averaged, Hydrodynamic and Water Quality Model, Version 2.0. User Manual. , 1995 .

[31]  Kwang-Seuk Jeong,et al.  Delayed influence of dam storage and discharge on the determination of seasonal proliferations of Microcystis aeruginosa and Stephanodiscus hantzschii in a regulated river system of the lower Nakdong River (South Korea). , 2007, Water research.

[32]  Xin Yao,et al.  Evolving neural networks for chlorophyll-a prediction , 2001, Proceedings Fourth International Conference on Computational Intelligence and Multimedia Applications. ICCIMA 2001.

[33]  A. Peterson,et al.  Predicting distributions of Mexican birds using ecological niche modelling methods , 2002 .

[34]  Arup Kumar Sarma,et al.  Genetic Algorithm for Optimal Operating Policy of a Multipurpose Reservoir , 2005 .

[35]  Min-Ho Jang,et al.  Winter Stephanodiscus bloom development in the Nakdong River regulated by an estuary dam and tributaries , 2003, Hydrobiologia.

[36]  Pei Hongping,et al.  Study on the algal dynamic model for West Lake, Hangzhou , 2002 .

[37]  Eun-Shik Kim,et al.  Current status of Korea Long-Term Ecological Research (KLTER) Network activities compared with the framework activities of the Long-Term Ecological Research (LTER) Networks of the United States and China , 2011 .

[38]  Nguyen Xuan Hoai,et al.  Ecological application of evolutionary computation: Improving water quality forecasts for the Nakdong River, Korea , 2010, IEEE Congress on Evolutionary Computation.

[39]  Peter A. Whigham,et al.  An inductive approach to ecological time series modelling by evolutionary computation , 2001 .

[40]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[41]  David Paull,et al.  Machine learning of poorly predictable ecological data , 2006 .

[42]  J. Cho,et al.  A river water quality management model for optimising regional wastewater treatment using a genetic algorithm. , 2004, Journal of environmental management.

[43]  Lars Håkanson,et al.  A general dynamic model to predict biomass and production of phytoplankton in lakes , 2003 .