Forecasting PM10 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 hi...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , , |
Language: | English |
Published: |
MDPI
2023
|
Subjects: | |
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 |
id |
ftjrc:oai:publications.jrc.ec.europa.eu:JRC134016 |
---|---|
record_format |
openpolar |
spelling |
ftjrc:oai:publications.jrc.ec.europa.eu:JRC134016 2023-09-05T13:17:04+02:00 Forecasting PM10 levels using machine learning models in the Arctic: a comparative study FAZZINI Paolo MONTUORI Marco PASINI Antonello CUZZUCOLI Alice CROTTI Ilaria CAMPANA Emilio PETRACCHINI Francesco DOBRICIC Srdan 2023 Online https://publications.jrc.ec.europa.eu/repository/handle/JRC134016 https://www.mdpi.com/2072-4292/15/13/3348 https://doi.org/10.3390/rs15133348 eng eng MDPI JRC134016 2023 ftjrc https://doi.org/10.3390/rs15133348 2023-08-16T22:28:24Z 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 Other/Unknown Material Arctic Tromso Tromso Joint Research Centre, European Commission: JRC Publications Repository Arctic Tromso ENVELOPE(16.546,16.546,68.801,68.801) Remote Sensing 15 13 3348 |
institution |
Open Polar |
collection |
Joint Research Centre, European Commission: JRC Publications Repository |
op_collection_id |
ftjrc |
language |
English |
description |
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 |
author |
FAZZINI Paolo MONTUORI Marco PASINI Antonello CUZZUCOLI Alice CROTTI Ilaria CAMPANA Emilio PETRACCHINI Francesco DOBRICIC Srdan |
spellingShingle |
FAZZINI Paolo MONTUORI Marco PASINI Antonello CUZZUCOLI Alice CROTTI Ilaria CAMPANA Emilio PETRACCHINI Francesco DOBRICIC Srdan Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
author_facet |
FAZZINI Paolo MONTUORI Marco PASINI Antonello CUZZUCOLI Alice CROTTI Ilaria CAMPANA Emilio PETRACCHINI Francesco DOBRICIC Srdan |
author_sort |
FAZZINI Paolo |
title |
Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
title_short |
Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
title_full |
Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
title_fullStr |
Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
title_full_unstemmed |
Forecasting PM10 levels using machine learning models in the Arctic: a comparative study |
title_sort |
forecasting pm10 levels using machine learning models in the arctic: a comparative study |
publisher |
MDPI |
publishDate |
2023 |
url |
https://publications.jrc.ec.europa.eu/repository/handle/JRC134016 https://www.mdpi.com/2072-4292/15/13/3348 https://doi.org/10.3390/rs15133348 |
long_lat |
ENVELOPE(16.546,16.546,68.801,68.801) |
geographic |
Arctic Tromso |
geographic_facet |
Arctic Tromso |
genre |
Arctic Tromso Tromso |
genre_facet |
Arctic Tromso Tromso |
op_relation |
JRC134016 |
op_doi |
https://doi.org/10.3390/rs15133348 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
13 |
container_start_page |
3348 |
_version_ |
1776198392699944960 |