The magnitude of bias in the measurement of PM2.5 arising from volatilization of particulate nitrate from teflon filters

Because the Federal Reference Method for PM2.5 specifies the collection of ambient particles on Teflon filters, we have examined the loss of a known volatile species, particulate nitrate, during sampling. Data are presented from two studies in southern California for which parallel samples were collected by different methods. Differences in collected nitrate are modeled using an evaporation model based on the work of Zhang and McMurry. The average nitrate obtained from sampling with Teflon filters was 28% lower on average than that measured by denuded nylon filters. In contrast, cascade impactor samples were within 5% of the denuded nylon filter on average. A simple model is presented that accounts for the particulate nitrate loss from Teflon filters either by scavenging nitric acid and ammonia in the sampler inlet or by heating the filter substrate during sampling. The observed magnitude of loss is explained by any of the following situations: (1) 100% nitric acid and ammonia vapor loss in the inlet, (2) 5 degrees C heating of the filter substrate above ambient temperature during sampling, or (3) a combination of these factors, such as 50% vapor loss in the inlet and 3 degrees C heating of the filter.