Integrating river hydromorphology and water quality into ecological status modelling by artificial neural networks.

The aim of the study was to develop predictive models of the ecological status of rivers by using artificial neural networks. The relationships between five macrophyte indices and the combined impact of water pollution as well as hydromorphological degradation were examined. The dataset consisted of hydromorphologically modified rivers representing a wide water quality gradient. Three ecological status indices, namely the Macrophyte Index for Rivers (MIR), the Macrophyte Biological Index for Rivers (IBMR) and the River Macrophyte Nutrient Index (RMNI), were tested. Moreover two diversity indices, species richness (N) and the Simpson index (D) were tested. Physico-chemical parameters reflecting both water quality and hydromorphological status were utilized as explanatory variables for the artificial neural networks. The best modelling quality in terms of high values of coefficients of determination and low values of the normalized root mean square error was obtained for the RMNI and the MIR networks. The networks constructed for IBMR, species richness and the Simpson index showed a lower degree of fit. In all cases, modelling quality improved by adding two hydromorphological indices to the pool of explanatory variables. The significant effect of these indices in the models was confirmed by sensitivity analysis. The research showed that ecological assessment of rivers based on macrophyte metrics does not only reflect the water quality but also the hydromorphological status.

[1]  Bahram Choubin,et al.  An ensemble forecast of semi‐arid rainfall using large‐scale climate predictors , 2017 .

[2]  J. Connell.  Diversity in tropical rain forests and coral reefs. , 1978, Science.

[3]  N Thompson Hobbs,et al.  Alternatives to statistical hypothesis testing in ecology: a guide to self teaching. , 2006, Ecological applications : a publication of the Ecological Society of America.

[4]  Salim Heddam,et al.  Secchi Disk Depth Estimation from Water Quality Parameters: Artificial Neural Network versus Multiple Linear Regression Models? , 2016, Environmental Processes.

[5]  T. Asaeda,et al.  Effects of mechanical stressors caused by mean flow and turbulence on aquatic plants with different morphologies , 2017 .

[6]  Á. Borja,et al.  The European Water Framework Directive at the age of 10: a critical review of the achievements with recommendations for the future. , 2010, The Science of the total environment.

[7]  R. Neves,et al.  Understanding multiple stressors in a Mediterranean basin: Combined effects of land use, water scarcity and nutrient enrichment. , 2018, The Science of the total environment.

[8]  F. Guérold,et al.  Are trophic and diversity indices based on macrophyte communities pertinent tools to monitor water quality? , 2002, Water research.

[9]  E. H. Simpson.  Measurement of Diversity , 1949, Nature.

[10]  S. Puijalon,et al.  Response of aquatic plants to abiotic factors: a review , 2011, Aquatic Sciences.

[11]  H. Daniel,et al.  A new method to assess water trophy and organic pollution – the Macrophyte Biological Index for Rivers (IBMR): its application to different types of river and pollution , 2006, Hydrobiologia.

[12]  Relationships between macrophyte vegetation and physical and chemical conditions in northwest German running waters , 2014 .

[13]  S. Birk,et al.  Comparative test of ecological assessment methods of lowland streams based on long-term monitoring data of macrophytes. , 2016, The Science of the total environment.

[14]  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.

[15]  Hehuan Liao,et al.  Interactive effects of water quality, physical habitat, and watershed anthropogenic activities on stream ecosystem health. , 2018, Water research.

[16]  Steven Hamblin,et al.  On the practical usage of genetic algorithms in ecology and evolution , 2013 .

[17]  Xi Xiao,et al.  A novel single-parameter approach for forecasting algal blooms. , 2017, Water research.

[18]  Daniel Gebler,et al.  Modeling of the river ecological status with macrophytes using artificial neural networks , 2017 .

[19]  M. Bowes,et al.  How green is my river? A new paradigm of eutrophication in rivers. , 2006, The Science of the total environment.

[20]  Desmond Fletcher,et al.  Forecasting with neural networks: An application using bankruptcy data , 1993, Inf. Manag..

[21]  Christine M. Happey,et al.  Ecology of Freshwater. , 1972 .

[22]  N. Willby,et al.  Towards harmonization of ecological quality classification: establishing common grounds in European macrophyte assessment for rivers , 2010, Hydrobiologia.

[23]  N. Willby,et al.  The applicability of macrophyte compositional metrics for assessing eutrophication in European lakes , 2014 .

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

[25]  Anne Lyche Solheim,et al.  Managing aquatic ecosystems and water resources under multiple stress--an introduction to the MARS project. , 2015, The Science of the total environment.

[26]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[27]  F. H. Dawson,et al.  Quality assessment using River Habitat Survey data , 1998 .

[28]  Young-Seuk Park,et al.  Artificial Neural Networks: Multilayer Perceptron for Ecological Modeling , 2016 .

[29]  A. Lorenz,et al.  Hydromorphological restoration stimulates river ecosystem metabolism , 2016 .

[30]  B. Moss,et al.  The Water Framework Directive: total environment or political compromise? , 2008, The Science of the total environment.

[31]  S. Schneider,et al.  How Do Environmental Parameters Relate to Macroinvertebrate Metrics? — Prospects for River Water Quality Assessment , 2014 .

[32]  J. Allan.  Landscapes and Riverscapes: The Influence of Land Use on Stream Ecosystems , 2004 .

[33]  P. Bispo,et al.  Modeling the species richness and abundance of lotic macroalgae based on habitat characteristics by artificial neural networks: a potentially useful tool for stream biomonitoring programs , 2017, Journal of Applied Phycology.

[34]  J. Evans,et al.  Sediment budget approach to understanding historical stages of the Ottawa River in the context of land-use change, northwestern Ohio and southeastern Michigan, USA , 2014 .

[35]  Paolo Vezza,et al.  A comparison of artificial neural networks and random forests to predict native fish species richness in Mediterranean rivers , 2013 .

[36]  R. Clarke,et al.  Eutrophication impacts on a river macrophyte. , 2010 .

[37]  Development of comprehensive river typology based on macrophytes in the mountain-lowland gradient of different Central European ecoregions , 2015, Hydrobiologia.

[38]  A. Baattrup‐Pedersen,et al.  Functional trait composition of aquatic plants can serve to disentangle multiple interacting stressors in lowland streams. , 2016, The Science of the total environment.

[39]  Krzysztof Szoszkiewicz,et al.  Assessment of sources of uncertainty in macrophyte surveys and the consequences for river classification , 2006, Hydrobiologia.

[40]  T. Pham,et al.  Prediction of cyanobacterial blooms in the Dau Tieng Reservoir using an artificial neural network , 2017 .

[41]  Suntae Hwang,et al.  Application of an artificial neural network (ANN) model for predicting mosquito abundances in urban areas , 2016, Ecol. Informatics.

[42]  John Davy-Bowker,et al.  European river plant communities: the importance of organic pollution and the usefulness of existing macrophyte metrics , 2006, Hydrobiologia.

[43]  R. Naiman,et al.  Freshwater biodiversity: importance, threats, status and conservation challenges , 2006, Biological reviews of the Cambridge Philosophical Society.

[44]  Distribution of aquatic plants in the Northern Vosges rivers: implications for biomonitoring and conservation , 2008 .

[45]  Ruprecht Düll,et al.  Zeigerwerte von Pflanzen in Mitteleuropa , 1992 .

[46]  Anne Courrat,et al.  Three hundred ways to assess Europe's surface waters: An almost complete overview of biological methods to implement the Water Framework Directive , 2012 .

[47]  Vahid Nourani,et al.  Sensitivity analysis of the artificial neural network outputs in simulation of the evaporation process at different climatologic regimes , 2012, Adv. Eng. Softw..

[48]  Lulu Kang,et al.  Predicting influent biochemical oxygen demand: Balancing energy demand and risk management. , 2018, Water research.

[49]  J. Potts,et al.  River macrophyte indices: not the Holy Grail! , 2012 .

[50]  J. Foerster,et al.  Ecological classification of macrophytes and phytobenthos for rivers in Germany according to the water framework directive , 2004 .

[51]  Damaris Zurell,et al.  Collinearity: a review of methods to deal with it and a simulation study evaluating their performance , 2013 .

[52]  N. Prat,et al.  Establishing physico-chemical reference conditions in Mediterranean streams according to the European Water Framework Directive. , 2012, Water research.

[53]  Hamid Darabi,et al.  River suspended sediment modelling using the CART model: A comparative study of machine learning techniques. , 2018, The Science of the total environment.

[54]  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 .

[55]  G. Wiegleb,et al.  Natural variation of macrophyte vegetation of lowland streams at the regional level , 2015 .

[56]  Edward J. Rykiel,et al.  Artificial intelligence and expert systems in ecology and natural resource management , 1989 .