The historical dataset of the meteorological variables was recorded by the Mexican National Water Council (Comisión Nacional del Agua, CONAGUA) ground station located at the city of Mérida, Yucatán, Mexico; the following variables were found: temperature (T), vapor pressure (P), and relative humidity (H). The range dates of the records were from January 1, 2000 to September 30, 2018, where there is a daily record of temperatures with minimum, maximum, and average units, resulting in nine readings provided for each day.
<p>The proliferation of efficient edge computing has enabled a paradigm shift of how we monitor and interpret urban air quality. Coupled with the dense spatiotemporal resolution realized from large-scale wireless sensor networks, we can achieve highly accurate realtime local inference of airborne pollutants. In this paper, we introduce a novel Deep Neural Network architecture targeted at latent time-series regression tasks from continuous, exogenous sensor measurements, based on the Transformer encoder scheme and designed for deployment on low-cost power-efficient edge processors.