Mustafa Üstüner

Faculty Member

Samsun University

Biography

Mustafa Üstüner is an assistant professor at Dept. of Climate Science and Meteorological Engineering at Samsun University.

Mustafa obtained his PhD from the Department of Geomatic Engineering at Yildiz Technical University, and was a visiting researcher in the Geo-Spatial Analytics Lab at the University of South Florida (USF), US and in the Department of Earth Observation, Institute of Geography at the Friedrich-Schiller-University of Jena (FSU Jena), Germany.

His main research interests include Polarimetric Synthetic Aperture Radar (PolSAR) Remote Sensing, Applied Machine Learning and particularly Hyperspectral Data Analysis. Recently, he is working on dimensionality reduction and classification of hyperspectral images.

As an editorial task, He has been serving as an associate editor for the European Journal of Remote Sensing and as one of the co-editors for the Turkish Journal of Remote Sensing. He received the award for Top Reviewers for Geosciences - September 2018 from Publons.

Interests

Remote Sensing and GIS
Applied Machine Learning
Pattern Recognition

Education

PhD in Geomatic Engineering (Remote Sensing and GIS), 2020

Yildiz Technical University
Master in Geomatic Engineering (Remote Sensing and GIS), 2014

Yildiz Technical University
BSc in Geodesy and Photogrammetry Engineering, 2010

Karadeniz Technical University

Selected Publications

Polarimetric Target Decompositions and Light Gradient Boosting Machine for Crop Classification: A Comparative Evaluation.

This paper tested the capabilities of different polarimetric target decompositions in crop classification, while using a recently launched ensemble learning algorithm—namely Light Gradient Boosting Machine (LightGBM).

Mustafa Üstüner, Füsun Balık Şanlı

In ISPRS International Journal of Geo-Information, 2019

PDF

An assessment of training data for agricultural land cover classification: a case study of Bafra, Türkiye

The purpose of this experimental research is to investigate the impact of the different training set size on supervised machine learning classifiers for the agricultural land cover classification in remote sensing.

Mustafa Üstüner, Fatih Fehmi Şimsek

In Earth Science Informatics, 2025

PDF

Analysis of the forest fire in the ‘Bohemian Switzerland’ National Park using Landsat-8 and Sentinel-5P in Google Earth Engine

The aim of the current study is the early detection of the changes in vegetation, air quality and temperature after a forest fire in the national park “Bohemian Switzerland” using remote sensing methods in the Czech Republic.

Furkan Yilgan, Markéta Miháliková, Recep Serdar Kara, Mustafa Üstüner

In Natural Hazards , 2025

PDF

Recent Publications

Balancing hyperspectral dimensionality reduction and information preservation for machine learning-based lithological classification using EnMAP hyperspectral imagery

EnMAP imagery combined with dimensionality reduction techniques significantly improves lithological mapping accuracy in geologically complex areas.

Soufiane Hajaj, Abderrazak El Harti, Amin Beiranvand Pour, Younes Khandouch, Mustafa Üstüner, Morteza Maali Amiri

PDF

Post-seismic structural assessment: advanced crack detection through complex feature extraction using pre-trained deep learning and machine learning integration.

This study aimed to automatically detect cracks/damages in the buildings in Diyarbakir city after the February 6, 2023 Kahramanmaras, Turkey earthquake.

Hatice Catal Reis, Veysel Turk, Mustafa Üstüner, Cagla Melisa Kaya Yildiz, Ramazan Tatli

PDF