Evaluation of models generated via hybrid evolutionary algorithms for the prediction of Microcystis concentrations in the Vaal Dam, South Africa

Cyanobacteria are responsible for many problems in drinking water treatment works (DWTW) because of their ability to produce cyanotoxins that potentially can have an adverse effect on consumer health.  Therefore, the monitoring of cyanobacteria in source waters entering DWTW has become an essential  part of drinking water treatment management. Managers of DWTW rely heavily on results from  physical, chemical and biological water quality analyses, from grab samples, for their management decisions. However, results of water quality analyses may be delayed from 3 h to 14 days depending on a magnitude of factors such as sampling, distance and accessibility to laboratory, laboratory sample turnaround times, specific methods used in analyses, etc. Therefore, the benefit to managers and production chemists to be able to forecast future events of high cyanobacterial cell concentrations in the source water is evident. During this study, physical, chemical and biological water quality data from samples taken from 2000 to 2009 in the Vaal Dam, supplying South Africa’s largest bulk drinking water treatment facility, were used to develop models for the prediction of the cyanobacterium Microcystis sp. in the source water (real-time prediction together with 7, 14 and 21 days in advance). Water quality data from the Vaal Dam from 2010–2012 were used to test these models. The model showing the most promising results for incorporation into a ‘Cyanobacterial Incident Management Protocol’ is the one predicting Microcystis sp. 7 days in advance. This model showed a square correlation coefficient (R 2 ) of 0.90 when tested with the testing dataset (chosen by bootstrapping from the 2000–2009 input dataset) and a R 2 of 0.53 when tested with the 3-year ‘unseen’ dataset from 2010–2012. Keywords : cyanobacteria, drinking water treatment works, prediction models, cyanobacterial incident management protocol, water safety plan

[1]  H. Börnick,et al.  Adsorption of geosmin and 2-methylisoborneol onto powdered activated carbon at non-equilibrium conditions: influence of NOM and process modelling. , 2011, Water research.

[2]  Jussi Meriluoto,et al.  Toxic : cyanobacterial monitoring and cyanotoxin analysis , 2005 .

[3]  Friedrich Recknagel,et al.  Inductive reasoning and forecasting of population dynamics of Cylindrospermopsis raciborskii in three sub-tropical reservoirs by evolutionary computation. , 2014, Harmful algae.

[4]  C. V. Ginkel,et al.  Investigating the applicability of ecological informatics modelling techniques for predicting harmfull algal blooms in hypertrophic reservoirs of South Africa , 2007 .

[5]  Friedrich Recknagel,et al.  Patternising phytoplankton dynamics of two shallow lakes in response to restoration measures by applying non-supervised artificial neural networks , 2007 .

[6]  D. Knappe,et al.  Algae Detection and Removal Strategies for Drinking Water Treatment Plants , 2004 .

[7]  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.

[8]  Friedrich Recknagel,et al.  Hybrid Evolutionary Algorithm for Rule Set Discovery in Time-Series Data to Forecast and Explain Algal Population Dynamics in Two Lakes Different in Morphometry and Eutrophication , 2006 .

[9]  Annette Davison,et al.  Water safety plan manual: Step-by-step risk management for drinking-water suppliers. , 2009 .

[10]  Friedrich Recknagel,et al.  Rule-based agents for forecasting algal population dynamics in freshwater lakes discovered by hybrid evolutionary algorithms , 2008, Ecol. Informatics.

[11]  Friedrich Recknagel,et al.  Ecological relationships, thresholds and time-lags determining phytoplankton community dynamics of Lake Kinneret, Israel elucidated by evolutionary computation and wavelets , 2013 .

[12]  J. Lund,et al.  The inverted microscope method of estimating algal numbers and the statistical basis of estimations by counting , 1958, Hydrobiologia.

[13]  A. E. Walsby,et al.  The pressure relationships of gas vacuoles , 1971, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[14]  Sandra Barnard,et al.  The dynamics of toxic Microcystis strains and microcystin production in two hypertrofic South African reservoirs , 2012 .

[15]  Ajith Abraham,et al.  Hybrid Evolutionary Algorithms: Methodologies, Architectures, and Reviews , 2007 .

[16]  C.J.F. ter Braak,et al.  CANOCO - a FORTRAN program for canonical community ordination by [partial] [etrended] [canonical] correspondence analysis, principal components analysis and redundancy analysis (version 2.1) , 1988 .

[17]  Friedrich Recknagel,et al.  Generic limnological models on the touchstone: Testing the lake simulation library SALMO-OO and the rule-based Microcystis agent for warm-monomictic hypertrophic lakes in South Africa , 2008 .