Improving Forest Detection Using Machine Learning and Remote Sensing: A Case Study in Southeastern Serbia

Aug 3, 2026

Vegetation is central to ecosystem dynamics, and monitoring its spatial patterns and temporal change is essential for environmental resource management. This study investigates machine learning methods combined with remote sensing to increase the accuracy of forest detection in southeastern Serbia using Sentinel-2 multispectral bands. Public satellite data are processed with support vector machines implemented via scikit-learn in Python, testing vegetation indices to expand input parameters.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Materials and Methods

Sentinel-2 Data and Vegetation Indices

Machine Learning Model and Evaluation

Results

Discussion

Conclusion

applied sciences Article Improving Forest Detection Using Machine Learning and Remote Sensing: A Case Study in Southeastern Serbia Ivan Poti´c 1,†, Zoran Srdi´c 1,†, Boris Vakanjac 1, Saša Bakraˇc 1,2, *, Dejan Ðorevi´c 1,2, Radoje Bankovi´c 1,2 and Jasmina M. Jovanovi´c 3 Citation: Poti´c, I.; Srdi´c, Z.; Vakanjac, B.; Bakraˇc, S.; Ðorevi´c, D.; Bankovi´c, R.; Jovanovi´c, J.M. Improving Forest Detection Using Machine Learning and Remote Sensing: A Case Study in Southeastern Serbia. Appl. Sci. 2023, 13, 8289. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)app13148289 Academic Editors: Romano Lottering, Kabir Peerbhay and Samuel Adelabu Received: 12 June 2023 Revised: 10 July 2023 Accepted: 10 July 2023 Published: 18 July 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Military Geographical Institute “General Stevan Boškovi´c”, 11000 Belgrade, Serbia; [ipotic@gmail.com](ipotic@gmail.com) (I.P.); [zoran.m.srdic@gmail.com](zoran.m.srdic@gmail.com) (Z.S.); [borivac@gmail.com](borivac@gmail.com) (B.V.); [dejan.r.djordjevic@vs.rs](dejan.r.djordjevic@vs.rs) (D.Ð.); [radoje.bankovic@vs.rs](radoje.bankovic@vs.rs) (R.B.) 2 Military Academy, University of Defense, 11000 Belgrade, Serbia 3 Faculty of Geography, University of Belgrade, 11000 Belgrade, Serbia; [jasmina.jovanovic@gef.bg.ac.rs](jasmina.jovanovic@gef.bg.ac.rs) * Correspondence: [sasa.bakrac@vs.rs](sasa.bakrac@vs.rs); Tel.: +381-113205009 † Co-ﬁrst authors; these authors contributed equally to this work. Featured Application: The primary application of this work is in environmental resource management, speciﬁcally in the detection and monitoring of vegetation patterns and changes. By employing a machine learning approach, speciﬁcally the Support Vector Machines (SVM) algorithm, the study demonstrates that including vegetation indices alongside multispectral bands signiﬁcantly improves the accuracy of vegetation detection, achieving an overall classiﬁcation accuracy of up to 99.01%. The study's ﬁndings underscore the potential of machine learning and remote sensing in vegetation detection and monitoring and highlight the importance of incorporating vegetation indices to enhance classiﬁcation accuracy. The matter above has signiﬁcant implications for decision-making processes in environmental resource management, particularly in regions with diverse forest ecosystems. The potential applications of this work extend beyond the speciﬁc geographical context of the study. The methodology and ﬁndings could be applied to other regions and ecosystems, providing valuable insights for the preservation and conservation of forest ecosystems globally. Future research could further explore the applicability of these ﬁndings in different geographical regions and investigate other vegetation indices to improve the accuracy of forest detection and monitoring processes. Abstract: Vegetation plays an active role in ecosystem dynamics, and monitoring its patterns and changes is vital for effective environmental resource management. This study explores the possibility of machine learning techniques and remote sensing data to improve the accuracy of forest detection. The research focuses on the southeastern part of the Republic of Serbia as a case study area, using Sentinel-2 multispectral bands. The study employs publicly accessible satellite data and incorporates different vegetation indices to improve classification accuracy. The main objective is to examine the practicability of expanding the input parameters for forest detection using a machine learning approach. The classification process is performed by employing sup

FAQs

What case study area and data are used for forest detection?

The study uses southeastern Serbia as the case study area and Sentinel-2 multispectral satellite data to support forest detection experiments.

Which machine learning approach drives the classification?

Classification is performed using support vector machines (SVM), utilizing the SVM module in the scikit-learn package.

How do vegetation indices affect detection accuracy?

Including vegetation indices alongside multispectral bands significantly improves vegetation detection accuracy, reaching an overall classification accuracy up to 99.01% with selected indices combined with Sentinel-2 bands.

Aug 3, 2026

Upload by Emma Wilson