[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119802-en":3,"doc-seo-119802-105":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":20,"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},119802,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Interpretability of machine learning with hydrological applications","This doctoral thesis investigates interpretable machine learning by focusing on feature importance and feature effects, aiming to clarify how models drive predictions and how subsets of features shape partial behavior. Using Accumulative Local Effect (ALE) plots, it develops new approaches to derive insights on feature importance and combines them with other promising ML methods for hydrological use cases. It first analyzes catchment stormflow response through the contribution of sub-basins in a natural watershed. It then demonstrates that ML tools and feature importance measures can strengthen an early warning system based on monitored discharges at watershed cross-sections.","Università Commerciale “Luigi Bocconi”  \nPhD School  \nPhD program in Statistics Cycle: 34st  \nDisciplinary Field: SECS-S/01  \nInterpretability of machine learning with hydrological applications  \nAdvisor: Emanuele Borgonovo  \nCo-Advisor: Salvatore Grimaldi  \nPhD Thesis by Francesco Cappelli  \nID number: 3082267  \nAbstract  \nThis doctoral thesis focuses on the interpretability of the machine learning (ML) considering two specific topics to achieve a better interpretation of machine findings: feature importance and feature effects. Feature importance helps to identify features that drive the ML model response, while feature effects provide a visualization of the partial behavior of the ML model as a function of a subset of features. Exploiting one of the most powerful visualization tool, Accumulative Local Effect (ALE) plot, I develop new approaches to obtain insights on feature importance. Moreover, I employ these new techniques in combination with other promising ML methods in hydrological applications. First, I aim to understand a catchment hydrological response by investigating how sub-basins of a selected natural watershed contribute to its stormflow response. Second, I prove that using ML tools and feature importance measures helps to enhance an early warming system based on monitored discharges in specific watershed cross-sections.  \nContents  \n1 Introduction 11  \n1.1 Interpretability Methods in Machine Learning . . . . . . . . . . . . . . . . 11  \n1.2 Theoretical Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13  \n1.2.1 Graphical Tools and Feature Importance Measures in Machine Learning .................................... 13  \n1.2.2 Feature importance measures in Sensitivity Analysis ......... 22  \n1.2.3 Machine Learning models and performance measures ........ 28  \n1.2.4 Performance measures . . . . . . . . . . . . . . . . . . . . . . . . . 31  \n2 Feature Importance and Marginal Effects 33  \n2. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33  \n2.2 From Graphical Tools to Feature Importance   35  \n2.3 Large K, Numerical Noise, Bias, and an Alternative ............. 42  \n2.4 Numerical Experiments: Analytical Test Cases ................ 45  \n2.4.1 Ishigami function ............................ 46  \n2.4.2 Hooker et al. (2021) test case ..................... 49  \n2.5 Application: Boston Housing dataset ..................... 52  \n3 Hydrological application I-Feature importance measures to dissect the role of sub-basins in shaping the watershed hydrological response: a proof of concept 59  \n2 CONTENTS  \n3. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59  \n3.2 Materials and Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62  \n3.2.1 Watershed case study description . . . . . . . . . . . . . . . . . . . 62  \n3.2.2 HEC-HMS model implementation   63  \n3.3 Results and discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65  \n3.3.1 Hydrologic synthetic scenario . . . . . . . . . . . . . . . . . . . . . 65  \n3.3.2 Optimal ML method selection   68  \n3.3.3 Importance analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . 69  \n3.3.4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73  \n4 Hydrological Application: Designing flood forecasting systems using  \nmachine learning, feature importance measures and synthetic scenar  \nios 77  \n4. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77  \n4.2 The framework concept   80  \n4.3 Materials and methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81  \n4.3. 1 Performance indices . . . . . . . . . . . . . . . . . . . . . . . . . . . 82  \n4.3.2 Case study description: the Tiber river . . . . . . . . . . . . . . . 83  \n4.3.3 Flood hydrographs database description . . . . . . . . . . . . . . . 85  \n4.3.4 Analysis   86  \n4.4 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . .","cbCaiczj809baRGv","https://ap.wps.com/l/cbCaiczj809baRGv","pdf",4893662,1,141,"English","en",105,"# Introduction\n## Interpretability Methods in Machine Learning\n## Theoretical Background\n# Feature Importance and Marginal Effects\n## Introduction\n## From Graphical Tools to Feature Importance\n## Numerical Experiments\n## Application: Boston Housing dataset\n# Hydrological application I\n## Feature importance measures to dissect the role of sub-basins\n# Hydrological Application\n## Designing flood forecasting systems\n# Conclusion\n# Appendices","[{\"question\":\"What interpretability concepts does the thesis focus on?\",\"answer\":\"The thesis focuses on feature importance and feature effects, where feature importance identifies drivers of model responses and feature effects visualize partial model behavior as a function of selected feature subsets.\"},{\"question\":\"How does the thesis use Accumulative Local Effect (ALE) plots?\",\"answer\":\"It exploits ALE plots to develop new approaches for extracting insights about feature importance from machine learning models.\"},{\"question\":\"What are the two main hydrological applications?\",\"answer\":\"First, it studies how sub-basins contribute to catchment stormflow response. Second, it uses ML tools and feature importance measures to enhance an early warning system based on monitored discharges at specific watershed cross-sections.\"}]","Interpretability of machine learning with hydrological applications | PDF",1785726379,355,{"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},"interpretability-of-machine-learning-with-hydrological-applications","",{"@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/interpretability-of-machine-learning-with-hydrological-applications/119802/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What interpretability concepts does the thesis focus on?","Question",{"text":75,"@type":76},"The thesis focuses on feature importance and feature effects, where feature importance identifies drivers of model responses and feature effects visualize partial model behavior as a function of selected feature subsets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis use Accumulative Local Effect (ALE) plots?",{"text":80,"@type":76},"It exploits ALE plots to develop new approaches for extracting insights about feature importance from machine learning models.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the two main hydrological applications?",{"text":84,"@type":76},"First, it studies how sub-basins contribute to catchment stormflow response. Second, it uses ML tools and feature importance measures to enhance an early warning system based on monitored discharges at specific watershed cross-sections.","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"]