Quantitative Microbial Risk Assessment Framework Incorporating Water Ages with Legionella pneumophila Growth Rates.

Water age in drinking water systems is often used as a proxy for water quality but is rarely used as a direct input in assessing microbial risk. This study directly linked water ages in a premise plumbing system to concentrations of Legionella pneumophila via a growth model. In turn, the L. pneumophila concentrations were used for a quantitative microbial risk assessment to calculate the associated probabilities of infection (Pinf) and clinically severe illness (Pcsi) due to showering. Risk reductions achieved by purging devices, which reduce water age, were also quantified. The median annual Pinf exceeded the commonly used 1 in 10,000 (10-4) risk benchmark in all scenarios, but the median annual Pcsi was always 1-3 orders of magnitude below 10-4. The median annual Pcsi was lower in homes with two occupants (4.7 × 10-7) than with one occupant (7.5 × 10-7) due to more frequent use of water fixtures, which reduced water ages. The median annual Pcsi for homes with one occupant was reduced by 39-43% with scheduled purging 1-2 times per day. Smart purging devices, which purge only after a certain period of nonuse, maintained these lower annual Pcsi values while reducing additional water consumption by 45-62%.

Classification machine learning to detect de facto reuse and cyanobacteria at a drinking water intake.

Harmful algal blooms (HABs) or higher levels of de facto water reuse (DFR) can increase the levels of certain contaminants at drinking water intakes. Therefore, the goal of this study was to use multi-class supervised machine learning (SML) classification with data collected from six online instruments measuring fourteen total water quality parameters to detect cyanobacteria (corresponding to approximately 950 cells/mL, 2900 cells/mL, and 8600 cells/mL) or DFR (0.5, 1 and 2 % of wastewater effluent) events in the raw water entering an intake. Among 56 screened models from the caret package in R, four (mda, LogitBoost, bagFDAGCV, and xgbTree) were selected for optimization. mda had the greatest testing set accuracy, 98.09 %, after optimization with 7 false alerts. Some of the most important water parameters for the different models were phycocyanin-like fluorescence, UVA254, and pH. SML could detect algae blending events (estimated <9000 cells/mL) due in part to the phycocyanin-like fluorescence sensor. UVA254 helped identify higher concentrations of DFR. These results show that multi-class SML classification could be used at drinking water intakes in conjunction with online instrumentation to detect and differentiate HABs and DFR events. This could be used to create alert systems for the water utilities at the intake, rather than the finished water, so any adjustment to the treatment process could be implemented.