Detekcija snježnih površina u Alpama iz multispektralnih satelitskih snimaka korištenjem strojnog učenja u programskom jeziku R

master's thesis

• Title: Detekcija snježnih površina u Alpama iz multispektralnih satelitskih snimaka korištenjem strojnog učenja u programskom jeziku R : diplomski rad
• Title (english): Detection of snow surfaces in the Alps from multispectral satellite images using machine learning in R programming language : master's thesis
• Author: Josipa Subotić
• Mentor: Ivan Medved (mentor)
• Committee member: Ivan Medved (predsjednik povjerenstva)
• Committee member: Jasna Orešković (član povjerenstva)
• Committee member: Tomislav Korman (član povjerenstva)
• Granter: University of Zagreb; Faculty of Mining, Geology and Petroleum Engineering; (Department of Geophysical Exploration and Mine Surveying); Zagreb
• Defense date and country: 2024-09-30, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mining, Petroleum and Geology Engineering; Geological Engineering

Abstract

Svrha ovog rada je razvoj i evaluacija modela za detekciju snježnog pokrivača korištenjem algoritama strojnog učenja. Korištenjem multispektralnih satelitskih snimaka iz misije Sentinel-2 i naprednih algoritama poput randomForest, Support Vector Machine i Neural Network, cilj je točno klasificirati snježni pokrivač i druge klase poput stijena, urbanih područja, vode i vegetacije. Analizirani su spektralni potpisi snježnog pokrivača u različitim godišnjim razdobljima, čime je omogućeno stvaranje pouzdanih klasificiranih rastera za vizualizaciju i procjenu učinkovitosti modela.

Abstract (english)

The purpose of this work is to develop and evaluate a model for snow cover detection using machine learning algorithms. Using multispectral satellite images from the Sentinel-2 mission and advanced algorithms such as randomForest, Support Vector Machine and Neural Network, the goal is to accurately classify snow cover and other classes such as rocks, urban areas, water and vegetation. The spectral signatures of the snow cover in different periods of the year were analyzed, which enabled the creation of reliable classified rasters for visualization and evaluation of the model's effectiveness.

• Keywords: Sentinel-2; QGIS; R; RStudio; RF; SVM; NNET; Alpe; Italija; Austrija; snijeg; urbano područje; vegetacija; stijene; voda
• Keywords (english): Sentinel-2; QGIS; R; RStudio; RF; SVM; NNET; Alps; Italy; Austria; snow; urban area; vegetation; rocks; water
• Language: croatian
• URN:NBN: urn:nbn:hr:169:726499
• Study programme: Title: Geological engineering; specializations in: Hydrogeology and engineering geology, Environmental geology; Course: Hydrogeology and engineering geology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka geološkog inženjerstva (magistar/magistra inženjer/inženjerka geološkog inženjerstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2025-01-16 08:30:25