<?xml version="1.0"?><rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:edm="http://www.europeana.eu/schemas/edm/" xmlns:wgs84_pos="http://www.w3.org/2003/01/geo/wgs84_pos" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:rdaGr2="http://rdvocab.info/ElementsGr2" xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:ore="http://www.openarchives.org/ore/terms/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:dcterms="http://purl.org/dc/terms/"><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-BD1LCJ6V/e5e74d15-669f-413f-aa7d-5bf516c9a222/IMAGE"><dcterms:extent>99 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-BD1LCJ6V/d2871907-8002-4b70-b0d9-ec24a7c27af7/PDF"><dcterms:extent>12571 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-BD1LCJ6V/097cbdfd-8441-4ed7-84e7-c92e829ecdf8/TEXT"><dcterms:extent>422 KB</dcterms:extent></edm:WebResource><edm:ProvidedCHO rdf:about="URN:NBN:SI:DOC-BD1LCJ6V"><dcterms:issued>2026</dcterms:issued><dc:contributor>Grčman, Helena</dc:contributor><dc:contributor>Grigillo, Dejan</dc:contributor><dc:contributor>Kokalj, Žiga</dc:contributor><dc:contributor>Kolar, Mitja</dc:contributor><dc:creator>Mangafić, Alen</dc:creator><dc:contributor>Oštir, Krištof</dc:contributor><dc:format xml:lang="sl">XX, 119 str., 24 str. pril., 30 cm</dc:format><dc:identifier>COBISSID_HOST:280466435</dc:identifier><dc:identifier>URN:URN:NBN:SI:doc-BD1LCJ6V</dc:identifier><dc:language>sl</dc:language><dc:publisher xml:lang="sl">A. Mangafić</dc:publisher><dc:source xml:lang="sl">visokošolska dela</dc:source><dc:subject xml:lang="sl">analiza tal</dc:subject><dc:subject xml:lang="en">civil engineering</dc:subject><dc:subject xml:lang="sl">daljinsko zaznavanje</dc:subject><dc:subject xml:lang="en">doctoral dissertation</dc:subject><dc:subject xml:lang="sl">doktorske disertacije</dc:subject><dc:subject xml:lang="en">environmental monitoring</dc:subject><dc:subject xml:lang="en">Environmental Protection</dc:subject><dc:subject xml:lang="en">heavy metals</dc:subject><dc:subject xml:lang="sl">hiperspektralno snemanje</dc:subject><dc:subject xml:lang="en">hyperspectral imaging</dc:subject><dc:subject xml:lang="en">imaging spectrometry</dc:subject><dc:subject xml:lang="sl">kemija tal</dc:subject><dc:subject xml:lang="en">machine learning</dc:subject><dc:subject xml:lang="sl">monitoring okolja</dc:subject><dc:subject xml:lang="sl">pedologija</dc:subject><dc:subject xml:lang="en">pedology</dc:subject><dc:subject xml:lang="en">remote sensing</dc:subject><dc:subject xml:lang="sl">slikovna spektrometrija</dc:subject><dc:subject xml:lang="en">soil analysis</dc:subject><dc:subject xml:lang="en">soil chemistry</dc:subject><dc:subject xml:lang="en">spectroradiometry</dc:subject><dc:subject xml:lang="sl">spektroradiometrija</dc:subject><dc:subject xml:lang="sl">strojno učenje</dc:subject><dc:subject xml:lang="sl">težke kovine</dc:subject><dc:subject xml:lang="sl">Varstvo okolja</dc:subject><dc:title xml:lang="sl">Določanje vsebnosti izbranih težkih kovin v tleh s hiperspektralnim daljinskim zaznavanjem| doktorska disertacija| Estimation of selected heavy metals concentrations in soil using hyperspectral remote sensing| doctoral dissertation|</dc:title><dc:description xml:lang="sl">This doctoral dissertation explores the use of hyperspectral remote sensing for predicting the content of heavy metals (Zn, Pb, Cd) in the upper soil layers. The research was conducted in the area northeast of Celje, where prolonged industrial activity has caused significant pollution. We developed a methodology based on linking airborne hyperspectral imagery with laboratory spectroradiometric measurements, as well as chemical and pedological analyses of soil samples. Attention is given to comprehensive data processing – from atmospheric correction, input data analysis, spectral transformations, and dataset preparation for modelling, to the selection of relevant variables. The influence of individual input variables and different preprocessing procedures on the quality of predictive models was assessed using conditional permutation importance. The final prediction of selected heavy metal contents is based on a novel approach using a machine learning method, where additional chemical and pedological variables are used only during the model training phase, while the final predictions rely exclusively on spectral data. The presented methodology constitutes a methodological contribution to the development of hyperspectral approaches for soil pollution monitoring and demonstrates potential for more efficient and cost-effective mapping over larger areas</dc:description><dc:description xml:lang="sl">V doktorski disertaciji obravnavamo uporabo hiperspektralnega daljinskega zaznavanja za napovedovanje vsebnosti težkih kovin (Zn, Pb, Cd) v zgornjih slojih tal. Raziskavo smo izvedli na območju severovzhodno od Celja, kjer je dolgotrajna industrijska dejavnost povzročila izrazito onesnaženje. Razvili smo metodologijo, ki temelji na povezavi letalskih hiperspektralnih posnetkov z laboratorijskimi spektroradiometričnimi meritvami ter kemijskimi in pedološkimi analizami vzorcev tal. Posebna pozornost je namenjena celoviti obdelavi podatkov – od atmosferskih popravkov, analize vhodnih podatkov, transformacij spektralnih vrednosti in priprave podatkovnih nizov za modeliranje do izbire relevantnih spremenljivk. Vpliv posameznih vhodnih spremenljivk in različnih postopkov predobdelave podatkov na kakovost napovednih modelov smo vrednotili s pogojno permutacijsko pomembnostjo. Končno napovedovanje vsebnosti izbranih težkih kovin temelji na novem pristopu, ki uporablja metodo strojnega učenja, pri čemer dodatne kemijsko-pedološke spremenljivke uporabimo zgolj v fazi učenja modelov, končne napovedi pa izvajamo izključno na spektralnih podatkih. Predstavljena metodologija je prispevek k razvoju hiperspektralnih metod za spremljanje onesnaženosti tal ter kaže potencial za učinkovitejše in stroškovno ugodnejše kartiranje na večjih območjih</dc:description><edm:type>TEXT</edm:type><dc:type xml:lang="sl">visokošolska dela</dc:type><dc:type xml:lang="en">theses and dissertations</dc:type><dc:type rdf:resource="http://www.wikidata.org/entity/Q1266946" /></edm:ProvidedCHO><ore:Aggregation rdf:about="http://www.dlib.si/?URN=URN:NBN:SI:DOC-BD1LCJ6V"><edm:aggregatedCHO rdf:resource="URN:NBN:SI:DOC-BD1LCJ6V" /><edm:isShownBy rdf:resource="http://www.dlib.si/stream/URN:NBN:SI:DOC-BD1LCJ6V/d2871907-8002-4b70-b0d9-ec24a7c27af7/PDF" /><edm:rights rdf:resource="http://rightsstatements.org/vocab/InC/1.0/" /><edm:provider>Slovenian National E-content Aggregator</edm:provider><edm:intermediateProvider xml:lang="en">National and University Library of Slovenia</edm:intermediateProvider><edm:dataProvider xml:lang="sl">Univerza v Ljubljani, Fakulteta za gradbeništvo in geodezijo</edm:dataProvider><edm:object rdf:resource="http://www.dlib.si/streamdb/URN:NBN:SI:DOC-BD1LCJ6V/maxi/edm" /><edm:isShownAt rdf:resource="http://www.dlib.si/details/URN:NBN:SI:DOC-BD1LCJ6V" /></ore:Aggregation></rdf:RDF>