Klasifikacija lave na Islandu pomoću multispektralnih snimaka Sentinel-2

master's thesis

• Title: Klasifikacija lave na Islandu pomoću multispektralnih snimaka Sentinel-2 : diplomski rad
• Title (english): Classification of lava in Iceland using Sentinel-2 multispectral images : master's thesis
• Author: Sara Talić
• 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: 2024-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mining, Petroleum and Geology Engineering; Geological Engineering

Abstract

Cilj ovog diplomskog rada je korištenje daljinskih istraživanja u svrhu klasificiranja lave na Islandu pomoću QGIS alata i njegovih dodataka. Kao posljedica niza erupcija vulkana krajem listopada 2023. godine u narednim mjesecima Island je iskusio niz zastrašujućih i opasnih situacija u kojima su bile potrebne mjere evakuacije. Korištenjem Sentinel-2 satelita preuzeta su dva seta podataka od kojih jedan predstavlja područje prije erupcije, a drugi poslije erupcije. Upotrebom SCP plugina za QGIS softver napravljeni su treninzi za nadziranu klasifikaciju prije i poslije erupcije lave. Algoritmi po kojima je rađena klasifikacija su maximum likelihood (maksimalna vjerojatnost), minumum distance (minimalna udaljenost) i spectral angle mapping (spektralno kutno kartiranje), sva tri algoritma korištena su na četiri treninga i uz promatranje samog njihovog rada, uspoređena je i ovisnost kvalitete treninga o dobivenim rezultatima.

Abstract (english)

The purpose of this thesis is to classify lava in Iceland using remote sensing and GIS tools and plugins. In the last months Iceland experienced multiple frightening and dangerous situations in which evacuation measures were necessary as a result of a series of volcanic eruptions at the end of October 2023. Two sets of Sentinel-2 satellite data were downloaded, one which represents area of interest before eruption and the other after. Using the SCP plugin for QGIS software, four training data sets were made to use for supervised classification on examples before and after lava. Algorithms used for the classification are maximum likelihood, minimum distance and spectral angle mapping, all three algorithms were trained on all four training sets. In the end, the quality analysis was performed to determine which algorithm is the most suitable.

• Keywords: Island; lava; klasifikacija; Sentinel-2; QGIS; SCP
• Keywords (english): Iceland; lava; classification; Sentinel-2; QGIS; SCP
• Language: croatian
• URN:NBN: urn:nbn:hr:169:769585
• 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: 2025-01-15 12:48:37