Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches

Phytoplankton biomass is an important indicator for water quality, and predicting its dynamics is thus regarded as one of the important issues in the domain of river ecology and management. However, the vast majority of models in river systems have focused mostly on flow prediction and water quality with very few applications to biotic parameters such as chlorophyll a (Chl a). Based on a 1.5-year measured dataset of Chl a and environmental variables, we developed two modeling approaches [artificial neural networks (ANN) and multiple linear regression (MLR)] to simulate the daily Chl a dynamics in a German lowland river. In general, the developed ANN and MLR models achieved satisfactory accuracy in predicting daily dynamics of Chl a concentrations. Although some peaks and lows were not predicted, the predicted and the observed data matched closely by the MLR model with the coefficient of determination (R2), Nash–Sutcliffe efficiency (NS), and the root mean square error (RMSE) of 0.53, 0.53, and 2.75 for the calibration period and 0.63, 0.62, and 1.94 for the validation period, respectively. Likewise, the results of the ANN model also illustrated a good agreement between observed and predicted data during calibration and validation periods, which was demonstrated by R2, NS, and RMSE values (0.68, 0.68, and 2.27 for the calibration period, 0.55, 0.66 and 2.12 for the validation period, respectively). According to the sensitivity analysis, Chl a concentration was highly sensitive to dissolved inorganic nitrogen, nitrate–nitrogen, autoregressive Chl a, chloride, sulfate, and total phosphorus. We concluded that it was possible to predict the daily Chl a dynamics in the German lowland river based on relevant environmental factors using either ANN or MLR models. The ANN model is well suited for solving non-linear and complex problems, while the MLR model can explicitly explore the coefficients between independent and dependent variables. Further studies are still needed to improve the accuracy of the developed models.

[1]  Tao Li,et al.  Spatial and temporal dynamics of phytoplankton and bacterioplankton biomass in Sanya Bay, northern South China Sea. , 2009, Journal of environmental sciences.

[2]  N. Fohrer,et al.  Modelling hydrological processes in mesoscale lowland river basins with SWAT—capabilities and challenges , 2008 .

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

[4]  Wan Ahmad Tajuddin Wan Abdullah,et al.  Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application , 2009, Comput. Geosci..

[5]  Carlos Dafonte,et al.  Integration of remote sensing techniques and connectionist models for decision support in fishing catches , 2007, Environ. Model. Softw..

[6]  F. Recknagel.  ANNA – Artificial Neural Network model for predicting species abundance and succession of blue-green algae , 1997, Hydrobiologia.

[7]  Rita B. Domingues,et al.  Phytoplankton and environmental variability in a dam regulated temperate estuary , 2007, Hydrobiologia.

[8]  S. Kristiansen.  Impact of increased river discharge on the phytoplankton community in the outer Oslofjord, Norway , 2004, Hydrobiologia.

[9]  Nicola Fohrer,et al.  Development and testing of a phytoplankton index of biotic integrity (P-IBI) for a German lowland river , 2012 .

[10]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[11]  Ingrid M. Schleiter,et al.  Modelling Ecological Interrelations in Running Water Ecosystems with Artificial Neural Networks , 2003 .

[12]  Edna Cabecinha,et al.  Multi-scale approach using phytoplankton as a first step towards the definition of the ecological status of reservoirs , 2009 .

[13]  R. J. Stevenson,et al.  Use of periphyton assemblage data as an index of biotic integrity , 2000, Journal of the North American Benthological Society.

[14]  S. I. V. Sousa,et al.  Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations , 2007, Environ. Model. Softw..

[15]  J. Elliott,et al.  Phytoplankton modelling of Lake Erken, Sweden by linking the models PROBE and PROTECH , 2007 .

[16]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[17]  J. Roldán,et al.  Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems , 2007 .

[18]  Qinghua Cai,et al.  Forecasting Daily Chlorophyll a Concentration during the Spring Phytoplankton Bloom Period in Xiangxi Bay of the Three-Gorges Reservoir by Means of a Recurrent Artificial Neural Network , 2009 .

[19]  G. Velde,et al.  Impact of hydrology on the chemistry and phytoplankton development in floodplain lakes along the Lower Rhine and Meuse , 1992 .

[20]  Gertraud Hotzel,et al.  Phytoplankton methods manual for australian freshwaters , 1999 .

[21]  A. E. Greenberg,et al.  Standard Methods for the Examination of Water and Wastewater seventh edition , 2013 .

[22]  Junfeng Gao,et al.  Hydrodynamic-phytoplankton model for short-term forecasts of phytoplankton in Lake Taihu, China , 2012 .

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

[24]  K. C. Mihalić,et al.  Spatial and temporal distribution of phytoplankton in a highly stratified estuary (Zrmanja, Adriatic Sea) , 2007 .

[25]  N. Fohrer,et al.  The impact of agricultural Best Management Practices on water quality in a North German lowland catchment , 2011, Environmental monitoring and assessment.

[26]  J. Arnold,et al.  VALIDATION OF THE SWAT MODEL ON A LARGE RWER BASIN WITH POINT AND NONPOINT SOURCES 1 , 2001 .

[27]  Nicola Fohrer,et al.  Incorporating landscape depressions and tile drainages of a northern German lowland catchment into a semi‐distributed model , 2010 .

[28]  Judit Padisák,et al.  Chlorophyll a concentration across a trophic gradient of lakes: An estimator of phytoplankton biomass? , 2008 .

[29]  F. Unrein,et al.  Phytoplankton response to pH rise in a N-limited floodplain lake: relevance of N2-fixing heterocystous cyanobacteria , 2010, Aquatic Sciences.

[30]  F. Pick,et al.  Longitudinal and seasonal development of planktonio chlorophyll a in the Rideau River, Ontario , 1995 .

[31]  H. Kloos,et al.  Comparative study of diatoms and macroinvertebrates as indicators of severe water pollution: Case study of the Kebena and Akaki rivers in Addis Ababa, Ethiopia , 2009 .

[32]  Jiantong Liu,et al.  Modeling of Cyanobacterial Blooms in Hypereutrophic Lake Dianchi, China , 2004 .

[33]  Edward J. Phlips,et al.  Meteorological influences on algal bloom potential in a nutrient‐rich blackwater river , 2007 .

[34]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[35]  Nicola Fohrer,et al.  Distribution of phytoplankton in a German lowland river in relation to environmental factors , 2010 .

[36]  H. Kuosa,et al.  Phytoplankton monitoring : the effect of sampling methods used during different stratification and bloom conditions in the Baltic Sea , 2009 .

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

[38]  Fernando Gustavo Tomasel,et al.  Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models , 1997 .

[39]  Thomas F. Cuffney,et al.  Comparison of watershed disturbance predictive models for stream benthic macroinvertebrates for three distinct ecoregions in western US , 2010 .

[40]  Krzysztof Szoszkiewicz,et al.  Assessment of european streams with diatoms, macrophytes, macroinvertebrates and fish : a comparative metric-based analysis of organism response to stress , 2006 .

[41]  A. Pinder,et al.  Modelling phytoplankton dynamics in the River Swale, an upland river in NE England , 1998 .

[42]  Ralph Smith,et al.  Limnology—Inland water ecosystems , 2002, Journal of the North American Benthological Society.

[43]  Michael Obach,et al.  Modelling population dynamics of aquatic insects with artificial neural networks , 2001 .

[44]  P. Kasprzak,et al.  Long term study on the influence of eutrophication, restoration and biomanipulation on the structure and development of phytoplankton communities in Feldberger Haussee (Baltic Lake District, Germany) , 1996, Hydrobiologia.

[45]  Alan H. Fielding,et al.  An introduction to machine learning methods , 1999 .

[46]  Horacio Zagarese,et al.  Annual patterns of phytoplankton density and primary production in a large, shallow lake: the central role of light. , 2009 .

[47]  Ingrid M. Schleiter,et al.  Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks , 1999 .

[48]  Edna Cabecinha,et al.  Multi-scale approach using phytoplankton as a first step towards the definition of reservoirs ecological status. , 2009 .

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

[50]  Friedrich Recknagel,et al.  Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent artificial neural network , 2001 .

[51]  A. E. Irish,et al.  Modelling Phytoplankton Dynamics in Fresh Waters: Affirmation of the PROTECH Approach to Simulation , 2010 .

[52]  B. Amiri,et al.  Comparative Prediction of Stream Water Total Nitrogen from Land Cover Using Artificial Neural Network and Multiple Linear Regression Approaches , 2009 .

[53]  Lu Zhi.  The model of chlorophyll-a concentration forecast in the West Lake based on wavelet analysis and BP neural networks , 2008 .

[54]  Nicola Fohrer,et al.  Modelling point and diffuse source pollution of nitrate in a rural lowland catchment using the SWAT model , 2010 .

[55]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[56]  Jennifer G. Winter,et al.  Epilithic diatoms as indicators of stream total N and total P concentration , 2000, Journal of the North American Benthological Society.

[57]  T. W. Barrett,et al.  Planning for the persistence of river biodiversity: exploring alternative futures using process‐based models , 2011 .

[58]  P. Pall,et al.  Temporal and spatial patterns of phytoplankton in a temperate lowland river (Emajogi, Estonia) , 2008 .

[59]  M. Laamanen,et al.  Long-term changes in summer phytoplankton communities of the open northern Baltic Sea , 2007 .