Klasifikacija litologije dijela sjevernog Velebita korištenjem multispektralnih satelitskih snimki Sentinel-2 u programskom jeziku R

master's thesis

• Title: Klasifikacija litologije dijela sjevernog Velebita korištenjem multispektralnih satelitskih snimki Sentinel-2 u programskom jeziku R : diplomski rad
• Title (english): Classification of lithology in the northern Velebit using multispectral Sentinel-2 satellite imagery in the R programming language : master's thesis
• Author: Laura Sziller
• 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: 2023-11-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mining, Petroleum and Geology Engineering; Geological Engineering

Abstract

Svrha ovog rada je klasifikacija litologije određenog područja korištenjem multispektralnih satelitskih snimaka i programa R, izradio se algoritam koji se može primijeniti za bilo koje područje istraživanja i klasifikaciju litologije područja. Korištenjem softvera QGIS, izrađeni su poligoni starosti i vrste stijena kao ulazni podaci za napravljeni algoritam. Prostorna analiza se dobila pomoću R-a, preko integriranog razvojnog okruženja RStudio-a. Korištenjem nadzirane klasifikacije sustav se uvježbao, dobio je podatke te na temelju stečenog znanja detektirao nove podatke povlačenjem sličnosti između njih. Rezultat istraživanja je grafički prikaz tri modela rf, svm i nnet, gdje se odabire pouzdaniji model koji sadrži litologiju s ostalim klasama i spektralni potpisi multispektralnih satelitskih snimki Sentinel-2. Rad se može upotrijebiti kao podloga budućim istraživanjima u svrhu pronalaska naprednijeg sustava detekcije litologije područja istraživanja, koja sadržava informacije o starosti i vrsti stijena, čime inženjerima geologije omogućava brže i ekonomičnije istraživanje i razumijevanje geoloških karakteristika terena.

Abstract (english)

The purpose of this study is the classification of lithology in a specific area using multispectral satellite imagery and the R programming language. An algorithm has been developed that can be applied to any research area for lithology classification. Using QGIS software, polygons of age and rock types were created as input data for the developed algorithm. Spatial analysis was performed using R through the integrated development environment of RStudio. Through supervised classification, the system was trained to acquire data and, based on the acquired knowledge, to detect new data by drawing similarities between them. The research results are graphically presented through three models: random forest (ri), support vector machine (svm), and neural network (nnet). The study aims to select the most reliable model that incorporates lithology with other classes and spectral signatures from Sentinel-2 multispectral satellite imagery. This work can serve as a foundation for future research aimed at developing an advanced system for detecting the lithology of research areas, including information about age and rock type. Such a system would enable geology engineers to conduct faster and more cost-effective research, enhancing their understanding of geological terrain characteristics.

• Keywords: klasifikacija; litologija; Sentinel-2; R; RStudio; QGIS; RF; SVM; NNET; vrsta stijene; starost stijene; nadzirana klasifikacija; spektralni potpis
• Keywords (english): classification; lithology; Sentinel-2; R; RStudio; QGIS; RF; SVM; NNET; rock type
• Language: croatian
• URN:NBN: urn:nbn:hr:169:337317
• 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: 2024-01-10 14:19:17