Evaluating performance of stormwater sampling approaches using a dynamic watershed model.

Accurate quantification of stormwater pollutant levels is essential for estimating overall contaminant discharge to receiving waters. Numerous sampling approaches exist that attempt to balance accuracy against the costs associated with the sampling method. This study employs a novel and practical approach of evaluating the accuracy of different stormwater monitoring methodologies using stormflows and constituent concentrations produced by a fully validated continuous simulation watershed model. A major advantage of using a watershed model to simulate pollutant concentrations is that a large number of storms representing a broad range of conditions can be applied in testing the various sampling approaches. Seventy-eight distinct methodologies were evaluated by "virtual samplings" of 166 simulated storms of varying size, intensity and duration, representing 14 years of storms in Ballona Creek near Los Angeles, California. The 78 methods can be grouped into four general strategies: volume-paced compositing, time-paced compositing, pollutograph sampling, and microsampling. The performances of each sampling strategy was evaluated by comparing the (1) median relative error between the virtually sampled and the true modeled event mean concentration (EMC) of each storm (accuracy), (2) median absolute deviation about the median or "MAD" of the relative error or (precision), and (3) the percentage of storms where sampling methods were within 10% of the true EMC (combined measures of accuracy and precision). Finally, costs associated with site setup, sampling, and laboratory analysis were estimated for each method. Pollutograph sampling consistently outperformed the other three methods both in terms of accuracy and precision, but was the most costly method evaluated. Time-paced sampling consistently underestimated while volume-paced sampling over estimated the storm EMCs. Microsampling performance approached that of pollutograph sampling at a substantial cost savings. The most efficient method for routine stormwater monitoring in terms of a balance between performance and cost was volume-paced microsampling, with variable sample pacing to ensure that the entirety of the storm was captured. Pollutograph sampling is recommended if the data are to be used for detailed analysis of runoff dynamics.

Relationship between rainfall and beach bacterial concentrations on Santa Monica bay beaches.

Rainfall effects on beach water quality in southern California are large enough that county health departments typically issue warnings for the public to avoid recreational water contact for 3 days following a storm. To enhance the scientific foundation for these preemptive public health warnings, we examined the relationship between rainfall and beach indicator bacteria concentrations using 5 years of fecal coliform data taken daily at 20 sites in southern California. There was a countrywide increase in ocean bacterial concentrations associated with almost all storms larger than 6 mm and with every storm larger than 25 mm. Only for storms less than 2.5 mm was there no observable rainfall effect. Bacterial concentrations remained elevated for 5 days following a storm, although they generally returned to levels below state water quality standards within 3 days. The length of the antecedent dry period had a minimal effect on this relationship, probably reflecting a quickly developed equilibrium between the decay of older fecal material and the introduction of new fecal material to the landscape.

Metals and bacteria partitioning to various size particles in Ballona Creek storm water runoff.

Many storm water best management practice (BMP) devices function primarily by capturing particulate matter to take advantage of the well-documented association between storm water particles and pollutants. The hydrodynamic separation or settling methods used by most BMP devices are most effective at capturing medium to large particles; however, these may not be the most predominant particles associated with urban runoff. The present study examined particle size distribution in storm water runoff from an urban watershed in southern California and investigated the pollutant-particle associations of metals (Cu, Pb, Ni, and Zn) and bacteria (enterococci and Escherichia coli). During small storm events (≤0.7 cm rain), the highest concentration of pollutants were associated with a <6-µm filter fraction, which accounted for 70% of the per storm contaminant mass but made up more than 20% of the total particle mass. The pollutant-particle association changed with storm size. Most pollutant mass was associated with >35 µm size particles during a 5-cm rain event. These results suggest that much of the contaminant load in storm water runoff will not be captured by the most commonly used BMP devices, because most of these devices (e.g., hydrodynamic separators) are unable to capture particles smaller than 75 µm.