[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128187-en":3,"doc-seo-128187-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128187,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Assessing the Key Drivers of Arctic Sea Ice Decline Through Machine Learning Techniques - Tesi di Laurea Magistrale","Arctic Amplification accelerates Arctic warming and intensifies sea-ice melt through feedbacks such as the ice-albedo effect, making rapid Arctic sea-ice decline a critical climate-change signal. The thesis investigates the key drivers behind reductions in Arctic sea-ice thickness using machine learning for automatic feature selection. It integrates multi-source datasets including PIOMAS sea-ice thickness, GHCN meteorology, Arctic river discharge (ArcticGRO), and teleconnections (NOAA). Three feature-selection algorithms are compared to extract predictive relationships. Results show broadly consistent driver identification, with IIS delivering the highest predictive accuracy; minimum and maximum temperatures dominate meteorological influence, while precipitation, snow variables, and river flows play secondary roles. Teleconnections, especially the Atlantic Multidecadal Oscillation, improve integration of hydro-meteorological information and predictive accuracy.","SCUOLA DI INGEGNERIA CIVILE, AMBIENTALE E TERRITORIALE  \nAssessing the Key Drivers of Arctic Sea Ice Decline Through Machine Learning Techniques  \nTesi di Laurea Magistrale in  \nGeoinformatics Engineering  \nIngegneria Geoinformatica  \nAuthor: Angelica Iseni e Ellen Poli  \nStudent ID: Angelica Iseni (10668862) -Ellen Poli (10728490)  \nAdvisor: Prof. Andrea Castelletti  \nCo-advisors: Dr. Matteo Sangiorgio, Dr. Jorge Pèrez-Aracil  \nAcademic Year: 2024-2025  \ni  \nAbstract  \nThe Arctic region is experiencing warming at a rate that is four times faster than the global average, a phenomenon known as Arctic Amplification. This warming is accelerating the melting of sea ice, which is contributing to feedback mechanisms such as the ice-albedo effect, where the retreating ice exposes darker ocean water that absorbs more heat, further exacerbating ice melt. The rapid decline of Arctic sea ice is one of the most significant indicators of climate change, with profound implications for the global climate system.  \nThis thesis explores the key drivers behind the reductions of Arctic sea ice thickness using machine learning techniques for feature selection, focusing on the role of hydrometeorological variables and teleconnections. To this aim, a variety of datasets are used, including sea ice thickness data from the Pan-Arctic Ice-Ocean Modeling and Assimilation System (PIOMAS), meteorological data from the Global Historical Climatology Network (GHCN), discharge from major Arctic rivers (ArcticGRO), and teleconnections (NOAA) . To tackle the complex and high-dimensional nature of the problem, machine learning algorithms are employed to unveil the relationships between drivers and sea ice thickness. The analysis relies on three automatic feature selection algorithms: the Wrapper for Quasi Equally Informative Subset Selection (W-QEISS), the Iterative Input Selection (IIS), and the Python Coral Reef Optimization with Substrate Layers (PyCRO-SL) .  \nThe results show that the three algorithms generally produce consistent outcomes, though some differences exist (e.g., PyCROSL is more inclusive) . The IIS input subset provides the highest predictive accuracy. Minimum and maximum temperatures stand out as the most influential meteorological drivers for the evolution of sea ice, while precipitation, snow-related variables, and river streamflows have a secondary role. Teleconnections, particularly the Atlantic Multidecadal Oscillation, emerge as key factors in integrating hydro-meteorological information and improving predictive accuracy, highlighting that the modeling of Arctic processes cannot ignore the interactions with processes outside the Polar region.  \nKeywords: Sea Ice Thickness, Arctic Amplification, Teleconnections, Arctic Rivers, PIOMAS, Climate Change, Automatic Feature Selection.  \nAbstract in lingua italiana  \nLa regione artica si riscalda a una velocità quattro volte superiore alla media globale, un fenomeno noto come Arctic Amplification. Questo riscaldamento accelera lo scioglimento del ghiaccio marino, favorendo meccanismi di feedback come l’effetto albedo, in cui il ghiaccio che si ritira espone acqua oceanica più scura che assorbe più calore, intensificando ulteriormente il riscaldamento. Il rapido declino del ghiaccio marino artico è uno dei principali indicatori del cambiamento climatico, con gravi implicazioni per il clima globale.  \nQuesta tesi esplora i fattori alla base delle riduzioni dello spessore del ghiaccio marino artico utilizzando tecniche di machine learning (ML) per la selezione delle variabili, concentrandosi sul ruolo delle variabili idrometeorologiche e delle teleconnessioni. A tal fine, sono utilizzati diversi set di dati, tra cui i dati sullo spessore del ghiaccio marino da Pan-Arctic Ice-Ocean Modeling and Assimilation System (PIOMAS), i dati meteorologicida Global Historical Climatology Network (GHCN), i deflussi dei principali fiumi artici (ArcticGRO) e le teleconnessioni (NOAA) . Per affrontare la natura co","cbCaidFWnAXxBBaO","https://ap.wps.com/l/cbCaidFWnAXxBBaO","pdf",15480843,2,1,134,"English","en",105,"# Contents\n## 1 Introduction\n## 2 State of the Art\n## 3 Materials and Methods","[{\"question\":\"What climate mechanism accelerates Arctic sea-ice decline in the thesis?\",\"answer\":\"The work highlights Arctic Amplification and the ice-albedo feedback: retreating ice exposes darker ocean water that absorbs more heat, further increasing ice melt.\"},{\"question\":\"Which datasets are used to study sea-ice thickness drivers?\",\"answer\":\"The thesis uses PIOMAS for sea-ice thickness, GHCN for meteorological variables, ArcticGRO for discharge from major Arctic rivers, and NOAA teleconnections.\"},{\"question\":\"How do the feature-selection algorithms compare, and which yields the best predictive performance?\",\"answer\":\"The three algorithms generally agree, but differ in inclusiveness. The IIS subset provides the highest predictive accuracy.\"}]","Assessing the Key Drivers of Arctic Sea Ice Decline Through Machine Learning Techniques - Tesi di Laurea Magistrale | PDF",1785945384,338,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"assessing-the-key-drivers-of-arctic-sea-ice-decline-through-machine-learning-techniques-masters-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/assessing-the-key-drivers-of-arctic-sea-ice-decline-through-machine-learning-techniques-masters-thesis/128187/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What climate mechanism accelerates Arctic sea-ice decline in the thesis?","Question",{"text":76,"@type":77},"The work highlights Arctic Amplification and the ice-albedo feedback: retreating ice exposes darker ocean water that absorbs more heat, further increasing ice melt.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which datasets are used to study sea-ice thickness drivers?",{"text":81,"@type":77},"The thesis uses PIOMAS for sea-ice thickness, GHCN for meteorological variables, ArcticGRO for discharge from major Arctic rivers, and NOAA teleconnections.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the feature-selection algorithms compare, and which yields the best predictive performance?",{"text":85,"@type":77},"The three algorithms generally agree, but differ in inclusiveness. The IIS subset provides the highest predictive accuracy.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]