A Multi-disciplinary Procedure to Ascertain Biofilm Formation in Drinking Water Pipes

Biofilm development in drinking water distribution systems (DWDSs) is a real problem negatively affecting service and water quality, and, thus, the satisfaction of the final consumers. It is the direct and indirect responsible for many of the DWDSs’ problems, and a lot of resources are invested to mitigate its effects. Addressing this problem has been a concern of researchers and DWDS managers for years. However, it is only recently that both technology and data have been available to support the new approach presented in this work. Our proposal is based on the combination of various existing data sets from similar studies to conduct a meta-data analysis of biofilm development. The approach lies on an intensive data pre-processing. Having a complete and extensive database on biofilm development in DWDSs allows applying Machine Learning techniques to develop a practical model. It is based on a multidisciplinary research vision to formulate effective biofilm control strategies. This work presents the basis for the development of a useful decision-making tool to assist in DWDS management. The negative effects on service and consumers caused by biofilm would be mitigated maintaining it at the lowest level. The performance of the suggested models is tested with data coming from two different case-studies: the DWDSs of the city of Thessaloniki (Greece) and the Pennine Water Group experimental facility (UK). The results obtained validate this methodology as an excellent approach to studying biofilm development in DWDSs.

[1]  Joaquín Izquierdo,et al.  Predictive models for forecasting hourly urban water demand , 2010 .

[2]  Nicola H. Green,et al.  Characterisation of the Physical Composition and Microbial Community Structure of Biofilms within a Model Full-Scale Drinking Water Distribution System , 2015, PloS one.

[3]  Blaz Zupan,et al.  Orange: From Experimental Machine Learning to Interactive Data Mining , 2004, PKDD.

[4]  Paul Monis,et al.  Assessing the impact of water treatment on bacterial biofilms in drinking water distribution systems using high-throughput DNA sequencing. , 2014, Chemosphere.

[5]  L. Melo,et al.  Impact of biofilms in simulated drinking water and urban heat supply systems , 2009 .

[6]  Eva Ramos Martínez,et al.  Assessing biofilm development in drinking water distribution systems by Machine Learning methods , 2016 .

[7]  Xiao-jian Zhang,et al.  Biofilm bacterial communities in urban drinking water distribution systems transporting waters with different purification strategies , 2014, Applied Microbiology and Biotechnology.

[8]  Miquel Sànchez-Marrè,et al.  On the role of pre and post-processing in environmental data mining , 2008 .

[9]  A. V. Van Soestbergen,et al.  Pour Plates or Streak Plates? , 1969, Applied microbiology.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  Andrew Barton,et al.  Biofilm development in water distribution and drainage systems: dynamics and implications for hydraulic efficiency , 2014 .

[12]  D. Reasoner.  Heterotrophic plate count methodology in the United States. , 2004, International journal of food microbiology.

[13]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[14]  B. Ripley,et al.  Recursive Partitioning and Regression Trees , 2015 .

[15]  Joaquín Izquierdo,et al.  Hybrid regression model for near real-time urban water demand forecasting , 2017, J. Comput. Appl. Math..

[16]  Joaquín Izquierdo,et al.  Ensemble of naïve Bayesian approaches for the study of biofilm development in drinking water distribution systems , 2014, Int. J. Comput. Math..

[17]  J H G Vreeburg,et al.  Discolouration in potable water distribution systems: a review. , 2007, Water research.

[18]  Daniel Rueckert,et al.  Random forest-based similarity measures for multi-modal classification of Alzheimer's disease , 2013, NeuroImage.