Air presence of particulate pollutants is an environmental problem with signi¯cant health issues. Monitoring their concentration is a key factor for the correct management of urban activities. In the smart cities scenario, the most fruitful tools for such application are sensor net- works combined with machine learning techniques. In this work, neural networks are employed to forecast particulate concentration of air pollutants using a novel multivariate approach. We analyzed ¯ve years of data relating to PM10 concentration, studying the performance of di®erent models based on the Long Short Term Memory paradigm, optimizing their hyperparameters ac- cordingly. The tests show good results in terms of approximation and generalization capabilities, along with a sensible dependence on the weather conditions.
Titolo: | Multivariate Prediction of PM10 Concentration by LSTM Neural Networks |
Autori: | |
Data di pubblicazione: | 2019 |
Abstract: | Air presence of particulate pollutants is an environmental problem with signi¯cant health issues. Monitoring their concentration is a key factor for the correct management of urban activities. In the smart cities scenario, the most fruitful tools for such application are sensor net- works combined with machine learning techniques. In this work, neural networks are employed to forecast particulate concentration of air pollutants using a novel multivariate approach. We analyzed ¯ve years of data relating to PM10 concentration, studying the performance of di®erent models based on the Long Short Term Memory paradigm, optimizing their hyperparameters ac- cordingly. The tests show good results in terms of approximation and generalization capabilities, along with a sensible dependence on the weather conditions. |
Handle: | http://hdl.handle.net/11697/153764 |
ISBN: | 978-1-7281-5305-6 |
Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |