Autonomous intake selection optimisation model for a dual source drinking water treatment plant

The Mudgeeraba drinking water treatment plant, in South-East Queensland, Australia, can withdraw raw water from two different reservoirs: the smaller Little Nerang dam (LND) by gravity, and the larger Advancetown Lake, through the use of pumps. Selecting the optimal intake is based on water quality and operators9 experience; however, there is potential to optimise this process. In this study, a comprehensive hybrid (data-driven, chemical, and mathematical) intake optimisation model was developed, which firstly predicts the chemicals dosages, and then the total (chemicals and pumping) costs based on the water quality at different depths of the two reservoirs, thus identifying the cheapest option. A second data-driven, probabilistic model then forecasts the volume of the smaller LND six weeks ahead in order to minimise the depletion and spill risks. This is important in case the first model identifies this reservoir as the optimal intake solution, but this could lead in the long term to depletion and full reliance on the electricity-dependent Advancetown Lake. Both models were validated and proved to be accurate, and with the potential for substantial monetary savings for the water utility.

[1]  Aini Hussain,et al.  Erratum to: Daily Forecasting of Dam Water Levels: Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS) , 2013, Water Resources Management.

[2]  D. Caldwell,et al.  Water Softening and Conditioning Problems , 1953 .

[3]  Özgür Kisi,et al.  Forecasting daily lake levels using artificial intelligence approaches , 2012, Comput. Geosci..

[4]  Victor Privalsky,et al.  Statistical Analysis and Predictability of Lake Erie Water Level Variations , 1992 .

[5]  Holger R. Maier,et al.  Use of artificial neural networks for predicting optimal alum doses and treated water quality parameters , 2004, Environ. Model. Softw..

[6]  Abdullahi Mohammed Evuti.  DEVELOPMENT OF A MODEL FOR THE ESTIMATION OF WATER TREATMENT COST: A DATA MINING APPROACH , 2013 .

[7]  Rodney Anthony Stewart,et al.  Medium-term storage volume prediction for optimum reservoir management: A hybrid data-driven approach , 2017 .

[8]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[9]  A. El-Shafie,et al.  Daily Forecasting of Dam Water Levels: Comparing a Support Vector Machine (SVM) Model With Adaptive Neuro Fuzzy Inference System (ANFIS) , 2013, Water Resources Management.

[10]  Roman Krzysztofowicz,et al.  The case for probabilistic forecasting in hydrology , 2001 .

[11]  Darshan Singh Sarai.  Water Treatment Made Simple: For Operators , 2005 .

[12]  Hong Zhang,et al.  An autonomous decision support system for manganese forecasting in subtropical water reservoirs , 2015, Environ. Model. Softw..

[13]  Hesham M. Bekhit,et al.  Using Markov Chain Monte Carlo to quantify parameter uncertainty and its effect on predictions of a groundwater flow model , 2009, Environ. Model. Softw..

[14]  E HassanAhmed,et al.  Using Markov Chain Monte Carlo to quantify parameter uncertainty and its effect on predictions of a groundwater flow model , 2009 .

[15]  Edoardo Bertone,et al.  Hybrid water treatment cost prediction model for raw water intake optimization , 2016, Environ. Model. Softw..

[16]  R. Stewart,et al.  International Conference on Hydroinformatics 8-1-2014 Numerical Study On Climate Variation And Population Growth Impacts On An Australian Subtropical Water Supply Reservoir , 2017 .

[17]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[18]  Gulay Tezel,et al.  Estimation of the Change in Lake Water Level by Artificial Intelligence Methods , 2014, Water Resources Management.