Abstract
Abstract. A high level of particulate matter in the atmosphere has an adverse long-term effect on human health. It has been associated with increased pulmonary tract and lung infections. It is more common in urban areas, especially megacities due to the confluence of industries and motorized machinery. Considering that most of the world’s population lives in urban areas, there is a need to monitor air pollution arising from particulate matter in order to ensure clean and safe air in cities in accordance with goal 11 of the Sustainable Development Goals. One way of doing this is through the use of Recurrent Neural Networks (RNN), which are suited for time varying data. Particulate matter concentration recorded by a network of low-cost sensors in Stuttgart is trained on three of the most popular RNN variants: Standard LSTM, Peephole LSTM and Gated Recurrent Unit. Two optimizers are used, Stochastic Gradient descent and Adam. Training is done on a single sensor and the optimum weights transferred and used in the prediction of other sensor values. This study concludes that Gated Recurrent Unit with Stochastic Gradient Descent is the most effective of the three variants in predicting particulate matter PM2.5 concentrations. In addition to this, weight transfer between sensors is not affected by temperature, wind direction, wind speed and geographic distance between sensors but rather by atmospheric pressure and the similarity of recorded Particulate matter levels.
Highlights
1.1 Particulate MatterParticulate matter is a complex mixture made up of Sulphates and organic compounds
The data used in this study consists of PM10 and PM2.5 measurements crowdsourced by OK Lab Stuttgart (OK Lab Stuttgart, 2019) as part of the ‘Hack your city’ citizen science project (Wissenschaft im Dialog, 2015) and hourly weather data composed of temperature, humidity, pressure, wind speed and wind direction obtained from OpenWeatherMap (OpenWeatherMap, 2019)
3 variants of recurrent neural networks and 2 optimizers resulting to 6 combinations have been evaluated and the Gated Recurrent Unit utilizing the Stochastic Gradient Descent (SGD) optimizer has been found to perform the best of the 6
Summary
Particulate matter is a complex mixture made up of Sulphates and organic compounds. It is one of 4 elements that cause air pollution, the other three being Ozone, Nitrogen dioxide and Sulphur dioxide (WHO Regional Office for Europe, 2003). Tapered Element Oscillating Microbalance (TEOM) provides for a near real time air quality index It determines particles concentration by monitoring changes in the oscillating frequency of a quartz glass tube during interaction with particles in the environment (Amaral et al, 2015). An environmentally aware public eager to participate in air pollution initiatives has created an ecosystem of volunteers and commercial entities manufacturing a wide variety of optical counters and their associated accessories (Karagulian et al, 2019). This has improved the spatial density of the particulate matter sensor grid and made available a huge pool of data that is transmitted and consumed in real time
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
