Detekcija snježnih površina u NP Paklenica pomoću Python programskog jezika

master's thesis

• Title: Detekcija snježnih površina u NP Paklenica pomoću Python programskog jezika : diplomski rad
• Title (english): Snow surface detection in NP Paklenica using Python programming language : master's thesis
• Author: Sven Keglević
• 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: 2020-09-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mining, Petroleum and Geology Engineering; Geological Engineering

Abstract

Na području Nacionalnog parka Paklenica analizira se stanje snježnog pokrova na temelju satelitskih snimki satelita Landsat 8 i Sentinel-2. Prikupljene su satelitske snimke područja snimljene unutar vremenskog perioda između listopada 2014. i svibnja 2020. godine. Pomoću zelenog i kratkovalnog infracrvenog kanala satelitskih snimaka računa se NDSI indeks, odnosno normaliziran indeks razlike u snijegu. Područja s pozitivnom vrijednosti NDSI indeksa su područja pod snježnim pokrivačem. Obrada podataka provodi se u programskom jeziku Python. Primjenjuje se analitička metoda računanja NDSI indeksa, te tri metode strojnog učenja: neuronske mreže, K-means i Mean shift metoda.

Abstract (english)

In the area of the Paklenica National Park, the condition of the snow cover is analyzed on the basis of satellite images of the Landsat 8 and Sentinel-2 satellites. Collected satellite images are taken within time period between October 2014 and May 2020. The NDSI index, ie the normalized snow difference index, is calculated using the green and shortwave infrared channels of satellite images. Areas with a positive NDSI index value are areas under snow cover. Data processing is performed in the Python programming language. The analytical method of NDSI index calculation is applied, as well as three machine learning methods: neural networks, K-means and Mean shift method.

• Keywords: Paklenica; daljinska istraživanja; satelitske snimke; snijeg; NDSI; Python; strojno učenje
• Keywords (english): remote sensing; satellite images; snow; NDSI; Python; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:169:514029
• Study programme: Title: Geological engineering; specializations in: Hydrogeology and engineering geology, Environmental geology; Course: Environmental 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: 2020-10-19 09:29:20