[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123681-en":3,"doc-seo-123681-105":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},123681,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Applying Machine Learning Models for Predicting Stream Network Dynamics - Master Thesis in Data Science","Intermittent streams sustain drinking-water quality and quantity, filter pollutants, support food supply and habitats, and mitigate flood risk. Their key trait is seasonal flow driven by groundwater and precipitation or snowmelt. From July 2018 to October 2021, the Valfredda catchment was monitored on 30 occasions to observe spatio-temporal river-network dynamics. Climatic and geomorphic data combined with machine learning predict node-state dynamics via binary classification, testing multiple feature sets and time ranges. Logistic regression, decision trees, random forests, k-nearest neighbors, and support vector machines are compared to identify the most accurate approach.","University of Padova  \nDepartment of Mathematics “Tullio Levi-Civita”  \nMaster Thesis in Data Science  \nApplying Machine Learning Models for Predicting Stream Network Dynamics  \nSupervisor Master Candidate  \nProf. Nicolo Navarin Sara Kartalovic  \nUniversity of Padova  \nCo-supervisor Student ID  \nProf. Gianluca Botter 2009468  \nUniversity of Padova  \nAcademic Year  \n2022-2023  \nii  \n“Today’s scientists have substituted mathematics for experiments, and they wander off through equation after equation, and eventually build a structure which has no relation to reality.”  \n—Nikola Tesla  \niv  \nAbstract  \nThe streams provide numerous benefits, some of which are maintaining the quality and quantity of drinking water, filtering pollutants, supplying food and providing habitat for wildlife and plants, and flood protection. The main characteristic of intermittent streams is the water flow during certain times of the year when groundwater and runoff from precipitation or snowmelt provide water for streamflow. Between July 2018 and October 2021, the study catchment Valfredda was monitored and the spatio-temporal dynamics ofthe active river network were observed on 30 occasions. In this study, climatic and geomorphic datasets and machine learning are used to predict the dynamics of intermittent streams along the Valfredda river in northern Italy. The prediction is made by performing the binary classification of the node’s state where various sets of features are explored in order to determine the measurable characterization of the fundamental causes and effects. Different time ranges were used to test the sensitivity of the nodes and the influence of time-series predictors. Machine learning classification algorithms logistic regression, decision tree, random forest, k-nearest neighbors, and support vector machine were evaluated using various metrics in order to select the best model. The classifiers were able to perform well across all versions of the dataset when historical information was included, but the weekly and biweekly approximations of the weather data were proven to be the best choice for accurate prediction because most of the best models were trained using this data. The weekly and biweekly approximation of all weather data features were calculated by taking the average of historical data 7 and 14 days before the date of observation respectively. On the other hand, when all data was included in the training of the model, the best models in both experiments were daily logistic regression models. In this case, the weather features included the values from one day before the observation day. The models suggest that spatio-temporal relations are crucial in prediction, and features such as weighted averages of the current and previous state of the node have a significant role in producing the correct output. Additionally, local persistency is essential for the majority of the models’ good performance.  \nvi  \nContents  \nAbstract v  \nList of figures viii  \nList of tables xi  \nListing of acronyms xiii  \n1 Introduction 1  \n2 Dataset 3  \n2.1 Shape Data .......................................... 4  \n2.1.1 Data Cleaning and Preprocessing .......................... 5  \n2.2 Weather Data ......................................... 7  \n2.2.1 Data Cleaning and Preprocessing .......................... 7  \n2.2.2 Data Analysis .................................... 8  \n2.3 Feature Engineering ...................................... 9  \n2.4 United Data Preprocessing .................................. 12  \n3 Methods 15  \n3.1 Models ............................................ 15  \n3.1.1 Logistic Regression ................................. 15  \n3.1.2 Decision Tree .................................... 17  \n3.1.3 Random Forest ................................... 18  \n3.1.4 K-nearest Neighbor ................................. 18  \n3.1.5 Support Vector Machine .............................. 19  \n3.2 Experiments .......................................... 20  ","cbCaibiEsv7H8IXE","https://ap.wps.com/l/cbCaibiEsv7H8IXE","pdf",2364066,1,51,"English","en",105,"# Abstract\n# Introduction\n# Dataset\n## Shape Data\n## Weather Data\n## Feature Engineering\n## United Data Preprocessing\n# Methods\n## Models\n## Experiments\n# Results\n## Baseline and Historical Data and Models\n## All Data and Models\n# Conclusion\n# References\n# Acknowledgments","[{\"question\":\"What problem does the thesis address about intermittent streams?\",\"answer\":\"It targets predicting the spatio-temporal dynamics of intermittent stream networks by modeling changes in node state over time.\"},{\"question\":\"How is prediction performed in the study?\",\"answer\":\"The work performs binary classification of each node’s state, exploring different feature sets and multiple time ranges for sensitivity and performance.\"},{\"question\":\"Which machine learning algorithms are evaluated and how is the best model chosen?\",\"answer\":\"Logistic regression, decision tree, random forest, k-nearest neighbors, and support vector machine are evaluated using multiple metrics to select the best-performing model under each dataset version.\"}]","Applying Machine Learning Models for Predicting Stream Network Dynamics - Master Thesis in Data Science | PDF",1785817982,129,{"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},"applying-machine-learning-models-for-predicting-stream-network-dynamics-master-thesis-in-data-science","",{"@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/applying-machine-learning-models-for-predicting-stream-network-dynamics-master-thesis-in-data-science/123681/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address about intermittent streams?","Question",{"text":75,"@type":76},"It targets predicting the spatio-temporal dynamics of intermittent stream networks by modeling changes in node state over time.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is prediction performed in the study?",{"text":80,"@type":76},"The work performs binary classification of each node’s state, exploring different feature sets and multiple time ranges for sensitivity and performance.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning algorithms are evaluated and how is the best model chosen?",{"text":84,"@type":76},"Logistic regression, decision tree, random forest, k-nearest neighbors, and support vector machine are evaluated using multiple metrics to select the best-performing model under each dataset version.","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"]