RESUMEN
Humidity- and temperature-dependent errors in concentrations reported by electrochemical sensors for atmospheric nitrogen dioxide significantly limit the reliability of the data. A basic understanding of the source of these errors has been missing. Empirical, software-based corrections are of limited reliability. The sensors feature a 40 wt % (≈4 molal) sulfuric acid electrolyte, and carbon working and quasi-reference (QRE) electrodes. We show that the sensor behaves as a truncated transmission line with resistance and capacitance elements varying with humidity. High-amplitude current fluctuations are due to humidity fluctuations, and are charging currents in response to fluctuations in interfacial capacitance. Baseline currents are due to very small differences in the open-circuit electrode potential between working and reference electrodes. We deduce that acid concentration changes in the meniscus within the porous electrode structure, in response to changes in the ambient temperature and humidity, cause both the capacitance fluctuations and the baseline changes. The open-circuit potential differences driving the baseline current variations are in part due to a difference in the liquid junction potential between the QRE and working electrode, dependent on humidity and temperature and caused by a gradient of acid concentration, and in part due to temperature- and acid-concentration-dependent variations in the rate of the potential-determining reactions. Based on the understanding obtained, we demonstrate a simple hardware change that corrects these unwanted errors.
Asunto(s)
Dióxido de Nitrógeno , Electrodos , Humedad , Reproducibilidad de los Resultados , TemperaturaRESUMEN
Aiming at minimizing the costs, both of capital expenditure and maintenance, of an extensive air-quality measurement network, we present simple statistical methods that do not require extensive training data sets for automated real-time verification of the reliability of data delivered by a spatially dense hybrid network of both low-cost and reference ozone measurement instruments. Ozone is a pollutant that has a relatively smooth spatial spread over a large scale although there can be significant small-scale variations. We take advantage of these characteristics and demonstrate detection of instrument calibration drift within a few days using a rolling 72 h comparison of hourly averaged data from the test instrument with that from suitably defined proxies. We define the required characteristics of the proxy measurements by working from a definition of the network purpose and specification, in this case reliable determination of the proportion of hourly averaged ozone measurements that are above a threshold in any given day, and detection of calibration drift of greater than ±30% in slope or ±5 parts-per-billion in offset. By analyzing results of a study of an extensive deployment of low-cost instruments in the Lower Fraser Valley, we demonstrate that proxies can be established using land-use criteria and that simple statistical comparisons can identify low-cost instruments that are not stable and therefore need replacing. We propose that a minimal set of compliant reference instruments can be used to verify the reliability of data from a much more extensive network of low-cost devices.
Asunto(s)
Contaminantes Atmosféricos/análisis , Monitoreo del Ambiente/normas , Ozono/análisis , Costos y Análisis de Costo , Monitoreo del Ambiente/economía , Humanos , Estándares de Referencia , Reproducibilidad de los ResultadosRESUMEN
A cost-efficient technology for accurate surface ozone monitoring using gas-sensitive semiconducting oxide (GSS) technology, solar power, and automated cell-phone communications was deployed and validated in a 50 sensor test-bed in the Lower Fraser Valley of British Columbia, over 3 months from May-September 2012. Before field deployment, the entire set of instruments was colocated with reference instruments for at least 48 h, comparing hourly averaged data. The standard error of estimate over a typical range 0-50 ppb for the set was 3 ± 2 ppb. Long-term accuracy was assessed over several months by colocation of a subset of ten instruments each at a different reference site. The differences (GSS-reference) of hourly average ozone concentration were normally distributed with mean -1 ppb and standard deviation 6 ppb (6000 measurement pairs). Instrument failures in the field were detected using network correlations and consistency checks on the raw sensor resistance data. Comparisons with modeled spatial O3 fields demonstrate the enhanced monitoring capability of a network that was a hybrid of low-cost and reference instruments, in which GSS sensors are used both to increase station density within a network as well as to extend monitoring into remote areas. This ambitious deployment exposed a number of challenges and lessons, including the logistical effort required to deploy and maintain sites over a summer period, and deficiencies in cell phone communications and battery life. Instrument failures at remote sites suggested that redundancy should be built into the network (especially at critical sites) as well as the possible addition of a "sleep-mode" for GSS monitors. At the network design phase, a more objective approach to optimize interstation distances, and the "information" content of the network is recommended. This study has demonstrated the utility and affordability of the GSS technology for a variety of applications, and the effectiveness of this technology as a means substantially and economically to extend the coverage of an air quality monitoring network. Low-cost, neighborhood-scale networks that produce reliable data can be envisaged.