Taste and odor problems can impede public trust in drinking water and impose major costs on water utilities. The ability to forecast taste and odor events in source waters, in advance, is shown for the first time in this paper. This could allow water utilities to adapt treatment, and where effective treatment is not available, consumers could be warned. A unique 24-year time series, from an important drinking water reservoir in Saskatchewan, Canada, is used to develop forecasting models of odor using chlorophyll a, turbidity, total phosphorus, temperature, and the following odor producing algae taxa: Anabaena spp., Aphanizemenon spp., Oscillatoria spp., Chlorophyta, Cyclotella spp., and Asterionella spp. We demonstrate, using linear regression and random forest models, that odor events can be forecast at 0-26 week time lags, and that the models are able to capture a significant increase in threshold odor number in the mid-1990s. Models with a fortnight time-lag show a high predictive capacity (R2 = 0.71 for random forest; 0.52 for linear regression). Predictive skill declines for time lags from 0 to 15 weeks, then increases again, to R2 values of 0.61 (random forest) and 0.48 (linear regression) at a 26-week lag. The random forest model is also able to provide accurate forecasting of TON levels requiring treatment 12 weeks in advance-93% true positive rate with a 0% false positive rate. Results of the random forest model demonstrate that phytoplankton taxonomic data outperform chlorophyll a in terms of predictive importance.
Scopus Subject Areas
- Environmental Chemistry