[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127075-en":3,"doc-seo-127075-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127075,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Forecasting PM10 Levels Using Machine Learning Models in the Arctic - A Comparative Study","This study presents a statistical forecasting framework to predict particulate matter (PM10) concentrations in the Arctic for Pallas (FI), Reykjavik (IS), and Tromso (NO). The framework combines historical ground measurements with 24 h predictions from nine Copernicus Atmosphere Monitoring Service (CAMS) models to generate PM10 forecasts. Model comparisons extend to different neural network memory cells, including RNNs, GRUs, LSTMs, ESNs, and windowed MLPs. Across memory-cell types, the framework achieves lower mean squared error (MSE) than CAMS models, with improvements of 25% to 40%, and evaluates the effect of outliers on performance.","remote sensing  \nArticle  \nForecasting PM 10 Levels Using Machine Learning Models in the Arctic: A Comparative Study  \nPaolo Fazzini 1,2, Marco Montuori 1,*, Antonello Pasini 2, Alice Cuzzucoli 2, Ilaria Crotti 3, Emilio Fortunato Campana 4, Francesco Petracchini 2 and Srdjan Dobricic 3  \n1 Institute for Complex Systems, National Research Council, 00185 Rome, Italy; [paolo.fazzini@sapienza.isc.cnr.it](paolo.fazzini@sapienza.isc.cnr.it)  \n2 Institute of Atmospheric Pollution Research, National Research Council, 00010 Rome, Italy; [pasini@iia.cnr.it](pasini@iia.cnr.it) (A.P.); [alice.cuzzucoli@iia.cnr.it](alice.cuzzucoli@iia.cnr.it) (A.C.); [petracchini@iia.cnr.it](petracchini@iia.cnr.it) (F.P.)  \n3 European Commission, Joint Research Centre, 21027 Ispra, Italy; ilaria.crotti@ec.europa.eu (I.C.); srdan.dobricic@ec.europa.eu (S.D.)  \n4 Department of Engineering, ICT and Technology for Energy and Transport, 00185 Rome, Italy; [emiliofortunato.campana@cnr.it](emiliofortunato.campana@cnr.it)  \n* [Correspondence: marco.montuori@cnr.it](Correspondence: marco.montuori@cnr.it)  \nCitation: Fazzini, P.; Montuori, M.; Pasini, A.; Cuzzucoli, A.; Crotti, I.; Campana, E.F.; Petracchini, F.; Dobricic, S. Forecasting PM10 Levels Using Machine Learning Models in the Arctic: A Comparative Study.  \nRemote Sens. 2023, 15, 3348. [https://](https://)[ ](https://)[doi.org/10.3390/rs15133348](doi.org/10.3390/rs15133348)  \nAcademic Editors: Yong Ge, Xiaomei Yang and Lianfa Li  \nReceived: 1 June 2023  \nRevised: 22 June 2023  \nAccepted: 25 June 2023  \nPublished: 30 June 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \nAbstract: 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 PM 10 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.  \nKeywords: deep learning; PM 10; environmental forecasting; chaotic time series; Arctic  \n1. Introduction  \nThe Arctic is warming at a faster rate compared with other areas of the Earth [1] . Environmental changes due to warming promote economic activities which increase anthropogenic emissions, while population growth amplifies the exposure to pollution [1] . Rising temperatures in the Arctic augment the risk of wildfires [2], representing a major natural source of atmospheric pollution. In the European Arctic, atmospheric pollution levels and exposure are lower compared with highly populated urban areas at middle latitudes [3] . Nevertheless, recent studies have raised concerns about the health effects of atmospheric pollution on the local population, generating an issue for public health and policymakers [1,4] . A limited number of atmospheric pollution monitoring stations are available in the Arctic to record concentrations at an hourly frequency. One of the m","cbCaieXkpM0WWNBJ","https://ap.wps.com/l/cbCaieXkpM0WWNBJ","pdf",2301344,1,26,"English","en",105,"# Introduction\n## Arctic warming and pollution drivers\n## PM10 definition and sources\n## Motivation and monitoring constraints\n# Forecasting Framework\n## Data sources and CAMS inputs\n## 24 h prediction strategy\n# Machine Learning Models\n## Memory cells in ANN-based approaches\n## Model comparison setup\n# Performance Evaluation\n## Error metrics and results vs CAMS\n## Outlier impact\n# Conclusion","[{\"question\":\"What locations and time horizon does the forecasting framework target?\",\"answer\":\"The framework predicts PM10 for Pallas (FI), Reykjavik (IS), and Tromso (NO) using a 24 h forecasting horizon.\"},{\"question\":\"How does the proposed method use CAMS information and ground measurements?\",\"answer\":\"It combines historical ground observations with 24 h predictions from nine CAMS models to produce PM10 forecasts for the following 24 hours.\"},{\"question\":\"Which neural network memory-cell variants are compared in the study?\",\"answer\":\"The study compares recurrent neural network variants using memory cells including RNNs, GRUs, LSTMs, echo state networks (ESNs), and windowed multilayer perceptrons (MLPs).\"},{\"question\":\"What performance gains are reported compared with CAMS models?\",\"answer\":\"The proposed framework reduces mean squared error (MSE) versus CAMS models, with average improvements ranging from 25% to 40%, and it also analyzes how outliers affect overall performance.\"}]","Forecasting PM10 Levels Using Machine Learning Models in the Arctic - A Comparative Study | PDF",1785936700,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"forecasting-pm10-levels-using-machine-learning-models-in-the-arctic-a-comparative-study","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/forecasting-pm10-levels-using-machine-learning-models-in-the-arctic-a-comparative-study/127075/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What locations and time horizon does the forecasting framework target?","Question",{"text":75,"@type":76},"The framework predicts PM10 for Pallas (FI), Reykjavik (IS), and Tromso (NO) using a 24 h forecasting horizon.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method use CAMS information and ground measurements?",{"text":80,"@type":76},"It combines historical ground observations with 24 h predictions from nine CAMS models to produce PM10 forecasts for the following 24 hours.",{"name":82,"@type":73,"acceptedAnswer":83},"Which neural network memory-cell variants are compared in the study?",{"text":84,"@type":76},"The study compares recurrent neural network variants using memory cells including RNNs, GRUs, LSTMs, echo state networks (ESNs), and windowed multilayer perceptrons (MLPs).",{"name":86,"@type":73,"acceptedAnswer":87},"What performance gains are reported compared with CAMS models?",{"text":88,"@type":76},"The proposed framework reduces mean squared error (MSE) versus CAMS models, with average improvements ranging from 25% to 40%, and it also analyzes how outliers affect overall performance.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]