Machine-Learning Classification of a Number of Contaminant Sources in an Urban Water Network

In the case of a contamination event in water distribution networks, several studies have considered different methods to determine contamination scenario information. It would be greatly beneficial to know the exact number of contaminant injection locations since some methods can only be applied in the case of a single injection location and others have greater efficiency. In this work, the Neural Network and Random Forest classifying algorithms are used to predict the number of contaminant injection locations. The prediction model is trained with data obtained from simulated contamination event scenarios with random injection starting time, duration, concentration value, and the number of injection locations which varies from 1 to 4. Classification is made to determine if single or multiple injection locations occurred, and to predict the exact number of injection locations. Data was obtained for two different benchmark networks, medium-sized network Net3 and large-sized Richmond network. Additionally, an investigation of sensor layouts, demand uncertainty, and fuzzy sensors on model accuracy is conducted. The proposed approach shows excellent accuracy in predicting if single or multiple contaminant injections in a water supply network occurred and good accuracy for the exact number of injection locations.

[1]  G. Freni,et al.  Impact of diffusion and dispersion of contaminants in water distribution networks modelling and monitoring , 2020, Water Supply.

[2]  S. Ranji Ranjithan,et al.  Contamination Source Identification in Water Distribution Systems Using an Adaptive Dynamic Optimization Procedure , 2011 .

[3]  Hui Wang,et al.  Improving Efficiency of the Bayesian Approach to Water Distribution Contaminant Source Characterization with Support Vector Regression , 2014 .

[4]  Edward A. McBean,et al.  Data mining to identify contaminant event locations in water distribution systems. , 2009 .

[5]  Tuqiao Zhang,et al.  Experimental study of solute mixing at double-Tee junctions in water distribution systems , 2015 .

[6]  Avi Ostfeld,et al.  A contamination source identification model for water distribution system security , 2007 .

[7]  Inanc Senocak,et al.  Stochastic reconstruction of multiple source atmospheric contaminant dispersion events , 2013 .

[8]  Y. Shao,et al.  Mixing at double-Tee junctions with unequal pipe sizes in water distribution systems. , 2016, Water science & technology, water supply.

[9]  L. Grbčić,et al.  Large Eddy Simulation of turbulent fluid mixing in double-tee junctions , 2020 .

[10]  A. Preis,et al.  Genetic algorithm for contaminant source characterization using imperfect sensors , 2008 .

[11]  Manuel A. Andrade,et al.  Mixing at junctions in water distribution systems: an experimental study , 2018 .

[12]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[13]  Lado Kranjčević,et al.  A Machine Learning-Based Algorithm for Water Network Contamination Source Localization , 2020, Sensors.

[14]  Yskandar Hamam,et al.  Towards Development of an Optimization Model to Identify Contamination Source in a Water Distribution Network , 2018 .

[15]  Lado Kranjčević,et al.  Efficient Double-Tee Junction Mixing Assessment by Machine Learning , 2020, Water.

[16]  G. Mahinthakumar,et al.  Contaminant Source Identification in Water Distribution Networks Under Conditions of Demand Uncertainty , 2009 .

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

[18]  Leslie Orear,et al.  Evaluation of solute mixing in water distribution pipe junctions , 2009 .

[19]  Li Liu,et al.  Identifying contaminant sources for water distribution systems using a hybrid method , 2012 .

[20]  Emily M. Zechman,et al.  Evolutionary Computation-Based Methods for Characterizing Contaminant Sources in a Water Distribution System , 2009 .

[21]  James G. Uber,et al.  Real-Time Identification of Possible Contamination Sources Using Network Backtracking Methods , 2010 .

[22]  Joseph Carroll,et al.  A Users Manual , 2012 .

[23]  Katherine A. Klise,et al.  Testing Contamination Source Identification Methods for Water Distribution Networks , 2016 .

[24]  Chuljin Park,et al.  Identification of a Contaminant Source Location in a River System Using Random Forest Models , 2018 .

[25]  L. Grbčić,et al.  Experimental and Numerical Investigation of Mixing Phenomena in Double-Tee Junctions , 2019, Water.

[26]  L. Grbčić,et al.  Water supply network pollution source identification by random forest algorithm , 2020 .

[27]  Avi Ostfeld,et al.  The Battle of the Water Sensor Networks (BWSN): A Design Challenge for Engineers and Algorithms , 2008 .

[28]  V. Rodriguez-Galiano,et al.  Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (Southern Spain). , 2014, The Science of the total environment.