Multivariate data mining for estimating the rate of discolouration material accumulation in drinking water distribution systems

Abstract

Particulate material accumulates over time as cohesive layers on internal pipeline surfaces in water distribution systems (WDS). When mobilised, this material can cause discolouration. This paper explores factors expected to be involved in this accumulation process. Two complementary machine learning methodologies are applied to significant amounts of real world field data from both a qualitative and a quantitative perspective. First, Kohonen self-organising maps were used for integrative and interpretative multivariate data mining of potential factors affecting accumulation.Second, evolutionary polynomial regression (EPR), a hybrid data-driven technique, was applied that combines genetic algorithms with numerical regression for developing easily interpretable mathematical model expressions. EPR was used to explore producing novel simple expressions to highlight important accumulation factors. Three case studies are presented: UK national and two Dutch local studies. The results highlight bulk water iron concentration, pipe material and looped network areas as key descriptive parameters for the UK study. At the local level, a significantly increased third data set allowed K-fold cross validation. The mean cross validation coefficient of determination was 0.945 for training data and 0.930 for testing data for an equation utilising amount of material mobilised and soil temperature for estimating daily regeneration rate. The approach shows promise for developing transferable expressions usable for pro-active WDS management.

Relating Water Quality and Age in Drinking Water Distribution Systems Using Self-Organising Maps

“…A key finding from the analysis is that the risk for water quality stagnation appears to be associated with high water age. SOMs have also been used to explore the factors contributing to higher material accumulation rates in water distribution pipeline systems [2].…”

“…Many of these are kinetic in nature and hence residence time within a system (or water age) may be an indicator of such deterioration [1]. It has also been shown that higher water temperatures may enhance water quality deterioration [2][3][4][5][6]. Many of the chemical changes that influence water quality are driven by reaction kinetics which are temperature dependent, and temperature also influences microbial populations [7].…”

“…Self-Organising Maps (SOMs) offer such an approach, having been previously applied for determining the parameters that influence the regeneration of discolouration material [2], and the influence of asset and hydraulic modelled parameters, including water age on the physical and chemical quality of drinking water [12].…”

Serious Gaming for Water Systems Planning and Management

“…However, it is possible using the developed game to manipulate pumps, valves and other system components in a similar fashion. Similarly, the game engine allows other type of WDS problems to be analysed, such as water quality issues [43], pump operations [44], leakage [45,46] and calibration [47], according to the needs of the game.…”

Modeling particle transport and discoloration risk in drinking water distribution networks

“…Field measurements from an extensive and prolonged program of cleaning actions that covers ∼ 450 km of pipes per year by Dutch water company PWN indicate that highturbidity events often occur in repeatable spatial and temporal patterns (Blokker and Schaap, 2011;Mounce et al, 2016). Factors that influence these patterns include the hydraulic vigor associated with the buildup and displacement of particles and sediment load from the treatment plant and transport mains upstream from the DWDS (Blokker and Schaap, 2015a).…”