Using urban sensor network data for spatio-temporal modelling of air quality risks
Speaker:
Vera van Zoest, University of Twente
Date and Time
September 27 2019, 14:15 - 15:00
Location
Polacksbacken, ITC 1211.
Abstract
In recently developed smart cities, sensor networks collect large amounts of data stored with spatial and temporal locations. Spatio-temporal data analysis techniques can be used to assess the data quality, filter data, and create meaningful products from these big datasets. This presentation covers the main results of the PhD research project “DAMAST”: Development of an Automatic system for Mapping Air quality risks in Space and Time. The research project aims to evaluate the usability of low-cost air quality sensor network data, including all steps of the data processing chain: from data quality evaluation (“making sense of sensor data”) to data application (“visualizing the invisible”). The main topics include outlier detection in low-cost sensor data, calibration of low-cost air quality sensor networks, modelling and mapping of air quality, and assessment of health risks related to air pollution. The low-cost air quality sensor network in Eindhoven, set up by the civil initiative AiREAS, is centrally used throughout the project. The developed methods and techniques are, however, widely applicable to sensor networks in general.