[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122494-en":3,"doc-seo-122494-105":30,"detail-sidebar-cat-0-en-105":91},{"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},122494,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Application of Machine Learning Methods for Landslide Risk Mitigation","Landslides in complex geological settings represent a widespread, high-impact hazard, intensified by climate change and placing major demands on modern emergency management. This PhD investigates landslide prediction and operational risk management in Emilia-Romagna, Italy, addressing obstacles in comprehensive susceptibility studies and timely response. Initial work improves rainfall thresholds by comparing empirical-statistical methods with machine learning models (e.g., XGBoost, Random Forest, neural networks), achieving higher accuracy and fewer false positives. A unified ML-based early-warning platform is developed, then rapid automated mapping is advanced after May 2023 events.","DOTTORATO DI RICERCA IN  \nSCIENZE DELLA TERRA, DELLA VITA E DELL'AMBIENTE  \nCiclo 37  \nSettore Concorsuale: 04/A3-GEOLOGIA APPLICATA, GEOGRAFIA FISICA E GEOMORFOLOGIA  \nSettore Scientifico Disciplinare: GEO/05-GEOLOGIA APPLICATA  \nAPPLICATION OF MACHINE LEARNING METHODS FOR LANDSLIDE RISK  \nMITIGATION  \nPresentata da: Nicola Dal Seno  \nCoordinatore Dottorato  \nBarbara Cavalazzi  \nSupervisore  \nMatteo Berti  \nCo-supervisore  \nElena Loli Piccolomini  \nEsame finale anno 2025  \nAbstract  \nLandslides in complex geological settings are a widespread and dangerous natural hazard that, in the context of climate change, poses significant challenges for modern society. Despite knowledge about triggering mechanisms and monitoring techniques, conducting comprehensive studies of landslide susceptibility and emergency management in regions like Emilia-Romagna, Italy, often entails significant obstacles. This PhD project analyzes the multifaceted aspects of landslide prediction and management in this geologically complex region.  \nThe research initially focused on improving rainfall thresholds for forecasting, comparing empirical-statistical approaches with machine learning (ML) techniques such as XGBoost, Random Forest, and neural networks. Results demonstrated that ML models outperformed traditional methods, achieving higher predictive accuracy and reducing false positives. While these techniques proved effective, challenges such as data quality and interpretability were highlighted, particularly in operational contexts. A key innovation was the development of a unified platform integrating ML-based rainfall thresholds into operational early warning systems, providing real-time risk assessments.  \nThe catastrophic rainfall events of May 2023 in Emilia-Romagna posed a significant challenge to our research, necessitating an unprecedented rapid response. These occurrences triggered thousands of landslides, underscoring the importance of swift and precise mapping for effective emergency management. Considering this urgent need, a multi-institutional collaboration was quickly established, leading to a comprehensive landslide inventory documenting 80,000 polygons using high-resolution aerial imagery. While invaluable for immediate recovery planning and future risk assessment, the time-consuming nature of manual mapping underscored the pressing need for faster, automated solutions. Our research pivoted to explore rapid automated mapping techniques, starting with trials using the U-Net neural network in severely affected municipalities like Casola Valsenio. More advanced algorithms, such as SegFormer, were subsequently employed across diverse settings including Modigliana, Predappio, and Brisighella. These methods demonstrated their ability to rapidly process large datasets, achieving high levels of accuracy in identifying landslide-affected areas. This urgent application of our research offered valuable insights into the practical challenges of rapid landslide response, informing innovations for future methodologies.  \nIn conclusion, this research demonstrates the transformative potential of integrating machine learning with traditional approaches in landslide prediction and management. Practical lessons learned include the importance of high-quality data, balancing interpretability with accuracy, and combining automated methods with expert validation for effective deployment in emergency contexts. The improved prediction models, early warning platform, comprehensive  \nlandslide inventory, and rapid mapping techniques collectively contribute to building resilient communities capable of effectively responding to and mitigating the impacts of landslides in the face of increasing climate-related risks.  \nCONTENTS  \nChapter 1 _________________________________________________________________ 6  \nIntroduction_______________________________________________________________ 6  \n1.1 Preface ______________________________________________________________ 6  \n","cbCaihRqc799Wr0J","https://ap.wps.com/l/cbCaihRqc799Wr0J","pdf",14664143,1,230,"English","en",105,"# Chapter 1: Introduction\n## Preface\n## Machine Learning: A Comprehensive Introduction\n## Machine Learning Real Use Cases for Civil Protection\n## Research questions and outline\n## References\n# Chapter 2\n## Comparative analysis of conventional and machine learning techniques for rainfall threshold evaluation under complex geological conditions\n## Preface\n## Abstract\n## Introduction\n## Study area\n## Methods","[{\"question\":\"Which machine learning models were used to improve rainfall thresholds for landslide forecasting?\",\"answer\":\"The project compares empirical-statistical approaches with machine learning methods including XGBoost, Random Forest, and neural networks.\"},{\"question\":\"What advantage did machine learning bring over traditional rainfall-threshold methods?\",\"answer\":\"Machine learning models achieved higher predictive accuracy and reduced false positives, although data quality and interpretability remained important challenges.\"},{\"question\":\"How did the May 2023 Emilia-Romagna rainfall events influence the research workflow?\",\"answer\":\"The events triggered thousands of landslides, requiring rapid mapping; this led to a large landslide inventory and then a shift toward faster automated mapping using U-Net and SegFormer.\"}]","Application of Machine Learning Methods for Landslide Risk Mitigation | PDF",1785810940,580,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"application-of-machine-learning-methods-for-landslide-risk-mitigation","",{"@graph":36,"@context":85},[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/application-of-machine-learning-methods-for-landslide-risk-mitigation/122494/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Which machine learning models were used to improve rainfall thresholds for landslide forecasting?","Question",{"text":75,"@type":76},"The project compares empirical-statistical approaches with machine learning methods including XGBoost, Random Forest, and neural networks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What advantage did machine learning bring over traditional rainfall-threshold methods?",{"text":80,"@type":76},"Machine learning models achieved higher predictive accuracy and reduced false positives, although data quality and interpretability remained important challenges.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the May 2023 Emilia-Romagna rainfall events influence the research workflow?",{"text":84,"@type":76},"The events triggered thousands of landslides, requiring rapid mapping; this led to a large landslide inventory and then a shift toward faster automated mapping using U-Net and SegFormer.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]