Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks

Air pollution has been shown to have a direct effect on human health. In particular, PM2.5 has been proven to be related to cardiovascular and respiratory problems. Therefore, it is important to have accurate models to predict high pollution events for this and other pollutants. We present different models that forecast PM2.5 maximum concentrations using a Long Short-Term Memory (LSTM) based neural network and a Deep Feedforward Neural Network (DFFNN). Ten years of air pollution and meteorological measurements from the network of monitoring stations in the city of Santiago, Chile were used, focusing on the behaviour of three zones of the city. All missing values were rebuilt using a method based on discrete cosine transforms and photochemical predictors selected through unsupervised clustering. Deep learning techniques provide significant improvements compared to a traditional multi-layer neural networks, particularly the LSTM model configured with a 7-day memory window (synoptic scale of pollution patterns) can capture critical pollution events at sites with both primary and secondary air pollution problems. Furthermore, the LSTM model consistently outperform deterministic models currently used in Santiago, Chile.

Automated summary

This study utilized air pollution and meteorological data from Santiago, Chile to accurately predict PM2.5 maximum concentrations using LSTM and DFFNN models. Deep learning techniques, particularly the LSTM model, provided significant improvements compared to traditional neural networks, outperforming deterministic models currently used in Santiago.