[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125280-en":3,"doc-seo-125280-105":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},125280,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Techniques For The Estimation Of Soil Moisture From Satellite Data - Master’s Thesis in Space Engineering","This study evaluates and compares machine learning algorithms to estimate surface soil moisture using satellite observations. The goal is to determine the most effective model architecture and to move toward a globally applicable “tool” for areas where in-situ stations are unavailable. The work uses TxSON (Texas, USA) for 2018–2021, Sentinel-1 dual-polarized radar (VH, VV) and Sentinel-2 vegetation information via NDVI, aligned with hourly ISMN time series. Model performance is assessed by minimizing RMSE.","Machine Learning Techniques For The Estimation Of Soil Moisture From Satellite Data  \nMaster’s Thesis in Space Engineering Marco Varalla, 991400  \nAdvisor:  \nProf. Claudio Maria Prati Politecnico di Milano  \nCo-advisors:  \nDr. Alfonso Amendola Eni S.p.A.  \nDr. Simone Sala Eni S.p.A.  \nAcademic year:  \n2022-2023  \nAbstract:  \nThe focus of this study is to evaluate and compare different types of machine learning algorithms for accurately estimating surface soil moisture using satellite data. The work aims to identify the most effective architecture for this purpose, striving to create a globally applicable \"tool\" that can be used in areas wherein-situ stations are not present.  \nThe chosen study area is the TxSON network in Texas, USA, characterized by arid conditions, uniform features, and sparse vegetation. The research covers a four-year period from January 1, 2018, to December 31, 2021 .  \nTo conduct this analysis, images with dual-polarized radar back-scatter (VH and VV polarizations) have been extracted from Sentinel-1, while red and near-infrared bands from Sentinel-2 have been used to calculate the Normalized Difference Vegetation Index (NDVI) . In total 115 satellite observations have been collected.  \nIn addition to satellite data, the study also incorporates in-situ data from the ISMN database, to retrieve soil moisture hourly time series. These data are later used for aligning and refining the machine learning models. Then the collected data have been partitioned into training and inference sets to develop a comprehensive database for analysis.  \nThe work evaluates various ML algorithms, including Linear, Random Forest (RF), Support Vector Machine (SVM), Gaussian Process Regression (GPR), Multi-Layer Perceptron (MLP) and others, with the aim to fine-tune the hyperparameters of these models to achieve the lowest possible Root Mean Square Error (RMSE), which serves as a measure of the accuracy of the models’ predictions.  \nHowever, after conducting the entire process and analyzing the outcomes, the research acknowledges that the results didn’t align with the intended objectives. In fact, the most noteworthy finding is the ’discovery’ that this workflow, specifically involving the training of algorithms for predicting soil moisture values, demonstrates its effectiveness when applied in a ’localized ’ approach.  \nThe task of training a ML model for a specific site and accurately predicting values in an different area, in order to achieve the initial goal of the research, the global tool, appears to be seemingly impossible.  \nKey-words: Soil moisture, Sentinel-1, Sentinel-2, VH & VV Polarization, NDVI, ML Algorithms  \nContents  \n1 Introduction 3  \n2 Study Area 4  \n3 Datasets 7  \n3.1 Satellite-Sentinel Program ....................................... 7  \n3.2 In-situ measurements ........................................... 9  \n4 Machine Learning Algorithms 10  \n5 Methodology 15  \n5.1 Satellite Data Pre-processing ...................................... 15  \n5.2 Machine Learning Phase (Training and Inference) ........................... 17  \n6 Results 19  \n7 Conclusions 21  \nA Appendix A 25  \nA.1 Soil Moisture Time Series ........................................ 25  \nA.2 Input vs Output Dependencies ..................................... 26  \nA.3 Linear Regression Model Results .................................... 27  \nA.4 Support Vector Machine Regression Model Results .......................... 29  \nA.5 Random Forest Regression Model Results ............................... 31  \nA.6 Ensemble of Learners Regression Model Results ............................ 33  \nA.7 Multi-Layer Perceptron Regression Model Results ........................... 35  \nA.8 Gaussian Process Regression Model Results .............................. 37  \nA.9 Gaussian Kernel Regression Model Results ............................... 39  \n1. Introduction  \nSoil moisture plays a crucial role as it quantifies the amount of water present within the soil matrix. T","cbCaip01zsz1gAa7","https://ap.wps.com/l/cbCaip01zsz1gAa7","pdf",24118432,1,44,"English","en",105,"# Introduction\n# Study Area\n# Datasets\n## Satellite-Sentinel Program\n## In-situ measurements\n# Machine Learning Algorithms\n# Methodology\n## Satellite Data Pre-processing\n## Machine Learning Phase (Training and Inference)\n# Results\n# Conclusions\n# Appendix A","[{\"question\":\"What is the main objective of the thesis?\",\"answer\":\"To compare multiple machine learning algorithms for accurately estimating surface soil moisture from satellite data and identify the most effective model architecture.\"},{\"question\":\"Which satellite data sources and features are used?\",\"answer\":\"Sentinel-1 dual-polarized radar backscatter (VH and VV) and Sentinel-2 red and near-infrared bands to compute NDVI are used for model inputs.\"},{\"question\":\"How is model accuracy evaluated in the study?\",\"answer\":\"Models are tuned to minimize Root Mean Square Error (RMSE), which measures the accuracy of soil moisture predictions.\"}]","Machine Learning Techniques For The Estimation Of Soil Moisture From Satellite Data - Master’s Thesis in Space Engineering | PDF",1785897938,111,{"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},"machine-learning-techniques-for-the-estimation-of-soil-moisture-from-satellite-data-masters-thesis-in-space-engineering","",{"@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/machine-learning-techniques-for-the-estimation-of-soil-moisture-from-satellite-data-masters-thesis-in-space-engineering/125280/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the thesis?","Question",{"text":75,"@type":76},"To compare multiple machine learning algorithms for accurately estimating surface soil moisture from satellite data and identify the most effective model architecture.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which satellite data sources and features are used?",{"text":80,"@type":76},"Sentinel-1 dual-polarized radar backscatter (VH and VV) and Sentinel-2 red and near-infrared bands to compute NDVI are used for model inputs.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model accuracy evaluated in the study?",{"text":84,"@type":76},"Models are tuned to minimize Root Mean Square Error (RMSE), which measures the accuracy of soil moisture predictions.","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"]