Forecasting PM10 levels using machine learning models in the Arctic: a comparative study

• Published in: Remote Sensing
• Main Authors: FAZZINI Paolo, MONTUORI Marco, PASINI Antonello, CUZZUCOLI Alice, CROTTI Ilaria, CAMPANA Emilio, PETRACCHINI Francesco, DOBRICIC Srdan
• Language: English
• Published: MDPI 2023
• Subjects: Arctic; Tromso
• Online Access: https://publications.jrc.ec.europa.eu/repository/handle/JRC134016; https://www.mdpi.com/2072-4292/15/13/3348; https://doi.org/10.3390/rs15133348

In this study, we present a statistical forecasting framework and assess its efficacy using a range of established machine learning algorithms for predicting Particulate Matter (PM) concentrations in the Arctic, specifically in Pallas (FI), Reykjavik (IS), and Tromso (NO). Our framework leverages historical ground measurements and 24 h predictions from nine models by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM10 predictions for the following 24 h. Furthermore, we compare the performance of various memory cells based on artificial neural networks (ANN), including recurrent neural networks (RNNs), gated recurrent units (GRUs), long short-term memory networks (LSTMs), echo state networks (ESNs), and windowed multilayer perceptrons (MLPs). Regardless of the type of memory cell chosen, our results consistently show that the proposed framework outperforms the CAMS models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Furthermore, we examine the impact of outliers on the overall performance of the model. JRC.C.5 - Clean Air and Climate