Srdjan Dobricic
Research Subjects
Research Interests
Srdjan Dobricic has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Alice Cuzzucoli
Institute of Atmospheric Pollution Research, National Research Council, 00010 Rome, Italy
1 shared publication - Antonello Pasini
Institute of Atmospheric Pollution Research, National Research Council, Monterotondo Stazione, 00015 Rome, Italy
1 shared publication - Emilio Fortunato Campana
CNR - Italian National Research Council, DIITET, Rome, Italy
1 shared publication - Francesco Petracchini
Institute of Atmospheric Pollution Research, National Research Council of Italy, c/o Area della Ricerca di Roma 1, Strada Provinciale 35d 9, 00010 Montelibretti, RM, Italy
1 shared publication - Ilaria Crotti
Joint Research Centre, European Commission, Ispra, Italy
1 shared publication - Marco Montuori
Institute of Complex Systems (ISC), National Research Council (CNR), 00185 Rome, Italy
1 shared publication
Latest Publications
- Open Access
- 5 June 2023
- Published by MDPI AG in Preprints.org
Forecasting PM Levels Using Machine Learning Models in the Arctic: A Comparative Study
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 measures and 24-hour predictions from 9 models provided by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM predictions for the following 24 hours. 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 multi-layer perceptrons (MLPs), which are commonly employed in time series forecasting tasks. Irrespective of the chosen memory cell type, our results demonstrate that the proposed framework consistently outperforms the CAM models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Additionally, we investigate the impact of outliers on the overall model performance.
- 5 June 2023
- Published by MDPI AG in Preprints.org
Open AccessForecasting PM Levels Using Machine Learning Models in the Arctic: A Comparative Study
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 measures and 24-hour predictions from 9 models provided by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM predictions for the following 24 hours. 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 multi-layer perceptrons (MLPs), which are commonly employed in time series forecasting tasks. Irrespective of the chosen memory cell type, our results demonstrate that the proposed framework consistently outperforms the CAM models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Additionally, we investigate the impact of outliers on the overall model performance.