Comparison of Nitrogen Dioxide Predictions During a Pandemic and Non-pandemic Scenario in the City of Madrid using a Convolutional LSTM Network

Traditionally, machine learning technologies with the methods and capabilities available, combined with a geospatial dimension, can perform predictive analyzes of air quality with greater accuracy. However, air pollution is influenced by many external factors, one of which has recently been caused by the restrictions applied to curb the relentless advance of COVID-19. These sudden changes in air quality levels can negatively influence current forecasting models. This work compares air pollution forecasts during a pandemic and non-pandemic period under the same conditions. The ConvLSTM algorithm was applied to predict the concentration of nitrogen dioxide using data from the air quality and meteorological stations in Madrid. The proposed model was applied for two scenarios: pandemic (January–June 2020) and non-pandemic (January–June 2019), each with sub-scenarios based on time granularity (1-h, 12-h, 24-h and 48-h) and combination of features. The Root Mean Square Error was taken as the estimation metric, and the results showed that the proposed method outperformed a reference model, and the feature selection technique significantly improved the overall accuracy.

Data on CO2, temperature and air humidity records in Spanish classrooms during the reopening of schools in the COVID-19 pandemic.

In order to reduce the advance of the pandemic produced by COVID-19, many actions and restrictions have been applied and the field of education has been no exception. In Spain, during the academic year 2020-2021, face-to-face teaching generally continued in both primary and secondary schools. Throughout the year, different measures have been taken to reduce the likelihood of contagion in classrooms, one of which was to improve ventilation by opening windows and doors. One of the most commonly used techniques to check for good ventilation has been CO2 monitoring. This work provides a set of 80,000 CO2 concentration records collected by low-cost Internet of Things nodes, primarily located within twelve classrooms in two primary schools. The published observations were collected between 1 May 2020 and 23 June 2021. Additionally, the same dataset includes temperature, air humidity and battery level observations.