Determination of sensitive variables regardless of hydrological alteration in artificial neural network model of chlorophyll a: Case study of Nakdong River

Abstract The Nakdong River has suffered from hydrological alterations in the river channel and riverine area during the Four Major Rivers Restoration Project (FMRRP). As these anthropogenic modifications have induced intensive algal blooms, the prediction of algal abundances has become an important issue for securing a source of drinking water and ecosystem stability. This study aimed to assess the changed river system in terms of chlorophyll a concentrations using artificial neural network (ANN) models trained for the pre-FMRRP period and tested for the post-FMRRP period in the middle reaches of such a river-reservoir system, and identify the descriptors that consistently affect algal dynamics. A total of 19 variables representing biweekly water-quality and meteo-hydrological data over 10 years were used to develop models based on different ANN algorithms. To identify the major descriptor to the algal dynamics, sensitivity analyses were performed. The best and most feasible model incorporating five parameters (wind velocity, conductivity, alkalinity, total nitrogen, and dam discharge) based on the topology of a probabilistic neural network with a smoothing parameter of 0.028 showed satisfactory results (R = 0.752, p

[1]  Z. Li,et al.  Determination of the Optimal Training Principle and Input Variables in Artificial Neural Network Model for the Biweekly Chlorophyll-a Prediction: A Case Study of the Yuqiao Reservoir, China , 2015, PloS one.

[2]  J. Burkholder,et al.  The Complex Relationships Between Increases in Fertilization of the Earth, Coastal Eutrophication and Proliferation of Harmful Algal Blooms , 2006 .

[3]  V. Denef,et al.  Cyanobacterial harmful algal blooms are a biological disturbance to Western Lake Erie bacterial communities , 2017, Environmental microbiology.

[4]  M. Pace,et al.  Dissolved organic carbon and nutrients as regulators of lake ecosystems: Resurrection of a more integrated paradigm , 1999 .

[5]  Shie-Yui Liong,et al.  An ANN application for water quality forecasting. , 2008, Marine pollution bulletin.

[6]  Dinesh Mohan,et al.  Multivariate statistical techniques for the evaluation of spatial and temporal variations in water quality of Gomti River (India)--a case study. , 2004, Water research.

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  Holger R. Maier,et al.  Flow management strategies to control blooms of the cyanobacterium, Anabaena circinalis, in the River Murray at Morgan, south Australia , 2001 .

[9]  C. Revenga,et al.  Fragmentation and Flow Regulation of the World's Large River Systems , 2005, Science.

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

[11]  Nicola Fohrer,et al.  Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches , 2013, Limnology.

[12]  S. Cheon,et al.  Occurrence and Succession Pattern of Cyanobacteria in the Upper Region of the Nakdong River : Factors Influencing Aphanizomenon Bloom , 2016 .

[13]  E. Moreno-Ostos,et al.  The residence time of river water in reservoirs , 2006 .

[14]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

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

[16]  Dong-Kyun Kim,et al.  River phytoplankton prediction model by Artificial Neural Network: Model performance and selection of input variables to predict time-series phytoplankton proliferations in a regulated river system , 2006, Ecological Informatics.

[17]  Gustaaf M. Hallegraeff,et al.  Harmful algal blooms: a global overview , 1995 .

[18]  Hakkwan Kim,et al.  Deriving Water Quality Criteria of Total Nitrogen for Nutrient Management in the Stream , 2015 .

[19]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[20]  C. S. Holling.  Resilience and Stability of Ecological Systems , 1973 .

[21]  Young-Seuk Park,et al.  Community patterning and identification of predominant factors in algal bloom in Daechung Reservoir (Korea) using artificial neural networks , 2007 .

[22]  Friedrich Recknagel,et al.  Response of Microcystis and Stephanodiscus to Alternative Flow Regimes of the Regulated River Nakdong (South Korea) Quantified By Model Ensembles Based on the Hybrid Evolutionary Algorithm (HEA) , 2017 .

[23]  Nico Salmaso,et al.  Factors controlling the seasonal development and distribution of the phytoplankton community in the lowland course of a large river in Northern Italy (River Adige) , 2008, Aquatic Ecology.

[24]  Joon Ha Kim,et al.  Development of early-warning protocol for predicting chlorophyll-a concentration using machine learning models in freshwater and estuarine reservoirs, Korea. , 2015, The Science of the total environment.

[25]  Sung-Nien Yu,et al.  Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network , 2007, Pattern Recognit. Lett..

[26]  T. J. Lah,et al.  The Four Major Rivers Restoration Project of South Korea , 2015 .

[27]  Guangwei Zhu,et al.  Dynamics of cyanobacterial bloom formation during short-term hydrodynamic fluctuation in a large shallow, eutrophic, and wind-exposed Lake Taihu, China , 2013, Environmental Science and Pollution Research.

[28]  H. Maier,et al.  Risk‐based approach for assessing the effectiveness of flow management in controlling cyanobacterial blooms in rivers , 2004 .

[29]  G. Palijan.  Abundance and Biomass Responses of Microbial Food Web Components to Hydrology and Environmental Gradients within a Floodplain of the River Danube , 2012, Microbial Ecology.

[30]  D. Fernández,et al.  Distribution of the bloom-forming diatom Didymosphenia geminata in the Ebro River basin (North-East Spain) in the period 2006-2009. , 2010 .

[31]  Bin Chen,et al.  Chlorophyll a Simulation in a Lake Ecosystem Using a Model with Wavelet Analysis and Artificial Neural Network , 2013, Environmental Management.

[32]  S. Interlandi,et al.  Recent water quality trends in the Schuylkill River, Pennsylvania, USA: a preliminary assessment of the relative influences of climate, river discharge and suburban development. , 2003, Water research.

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

[34]  Xiaodong Wu,et al.  Effects of Light and Wind Speed on the Vertical Distribution of Microcystis aeruginosa Colonies of Different Sizes during a Summer Bloom , 2009 .

[35]  Xi Cheng,et al.  Polynomial Regression As an Alternative to Neural Nets , 2018, ArXiv.

[36]  Hunter J. Carrick,et al.  Wind influences phytoplankton biomass and composition in a shallow, productive lake , 1993 .

[37]  B. H. Kim,et al.  Relationship between akinete germination and vegetative population of Anabaena flos-aquae (Nostocales, Cyanobacteria) in seokchon reservoir (Seoul, Korea) , 2005 .

[38]  H. Paerl,et al.  Nitrogen and phosphorus inputs control phytoplankton growth in eutrophic Lake Taihu, China , 2010 .

[39]  Alfred Wüest,et al.  Disrupting biogeochemical cycles - Consequences of damming , 2002, Aquatic Sciences.

[40]  T. Bridgeman,et al.  Summer phytoplankton nutrient limitation in Maumee Bay of Lake Erie during high-flow and low-flow years , 2014 .

[41]  Shan Lu.  Proceedings of the 8th Workshop on Programming Languages and Operating Systems , 2015, PLOS@SOSP.

[42]  Chong-Ho Choi,et al.  Sensitivity analysis of multilayer perceptron with differentiable activation functions , 1992, IEEE Trans. Neural Networks.

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

[44]  G. Joo,et al.  The phytoplankton succession in the lower part of hypertrophic Nakdong River (Mulgum), South Korea , 1998, Hydrobiologia.

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

[46]  J. Downing,et al.  The nitrogen : phosphorus relationship in lakes , 1992 .

[47]  J. Conroy,et al.  Soluble nitrogen and phosphorus excretion of exotic freshwater mussels (Dreissena spp.): potential impacts for nutrient remineralisation in western Lake Erie , 2005 .

[48]  Anna-Kristina Brunberg,et al.  THE IMPORTANCE OF SHALLOW SEDIMENTS IN THE RECRUITMENT OF ANABAENA AND APHANIZOMENON (CYANOPHYCEAE) 1 , 2004 .

[49]  Ling Chen,et al.  Effect of flow velocity on phytoplankton biomass and composition in a freshwater lake. , 2013, The Science of the total environment.

[50]  Hans W. Paerl,et al.  Harmful Freshwater Algal Blooms, With an Emphasis on Cyanobacteria , 2001, TheScientificWorldJournal.

[51]  R. O. Strobl,et al.  Application of artificial neural networks for classifying lake eutrophication status , 2007 .

[52]  M. Hosomi,et al.  Novel application of a back-propagation artificial neural network model formulated to predict algal bloom , 1997 .

[53]  G. Joo,et al.  Vertical distribution of Microcystis population in the regulated Nakdong River, Korea , 2000, Limnology.

[54]  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.

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