Comparative Analysis of Machine Learning Models for Sentinel-2 based Classification of the Bornean Heath Forest
Received: 11 January 2025 | Revised: 13 February 2025 | Accepted: 24 February 2025 | Online: 3 April 2025
Corresponding author: Kusrini
Abstract
Bornean heath forests, known as hutan kerangas, are fragile ecosystems that face significant anthropogenic threats. This study integrates Sentinel-2 satellite imagery with Machine Learning (ML) models to accurately classify these forests and assess their current spatial distribution. The Random Forest (RF) and Gradient Tree Boost (GTB) models achieved the highest classification performance, with overall accuracy scores of 96.66% and 96.69%, respectively, and Kappa coefficients of 0.945. These metrics were obtained using a test dataset with an 80:20 train-test split and validated through a 5-fold cross-validation process, ensuring the robustness of the models. Compared to previous studies employing unsupervised classification with Landsat-9 data, this approach demonstrates improved classification reliability and spatial accuracy. The findings highlight the substantial potential of combining remote sensing technologies with advanced ML techniques for large-scale ecosystem monitoring. This approach provides valuable insights for conservation planning and sustainable management of Bornean heath forests, addressing the growing environmental pressures that threaten their integrity.
Keywords:
heath forest classification, Sentinel-2 imagery, machine learning models, remote sensing, climateDownloads
References
R. M. Nisaa, U. K. Sari, and Y. B. Sulistioadi, "Heath forest identification using remote sensing in the surrounding area of the new capital city of Indonesia," IOP Conference Series: Earth and Environmental Science, vol. 1266, no. 1, Sep. 2023, Art. no. 012068.
M. A. Soendjoto, M. K. Riefani, and S. Diana, "Floristic diversity and composition of heath forest in Kuala Tambangan Village, Tanah Laut District, Indonesia," Biodiversitas Journal of Biological Diversity, vol. 24, no. 10, Nov. 2023.
I. S. Mohd Ikbal, S. Md Jaafar, N. Ahmad, and R. S. Sukri, "Contrasting environmental drivers of tree community variation within heath forests in Brunei Darussalam, Borneo," Biodiversity Data Journal, vol. 12, Dec. 2024, Art. no. e127919.
D. Oktavia, S. D. Pratiwi, S. Munawaroh, A. Hikmat, and I. Hilwan, "The potential of medicinal plants from heath forest: Local knowledge from Kelubi Village, Belitung Island, Indonesia," Biodiversitas Journal of Biological Diversity, vol. 23, no. 7, Jul. 2022.
M. A. Brovelli, Y. Sun, and V. Yordanov, "Monitoring Forest Change in the Amazon Using Multi-Temporal Remote Sensing Data and Machine Learning Classification on Google Earth Engine," ISPRS International Journal of Geo-Information, vol. 9, no. 10, Oct. 2020, Art. no. 580.
D. Hoekman et al., "Wide-Area Near-Real-Time Monitoring of Tropical Forest Degradation and Deforestation Using Sentinel-1," Remote Sensing, vol. 12, no. 19, Jan. 2020, Art. no. 3263.
Y. Gao, M. Skutsch, J. Paneque-Gálvez, and A. Ghilardi, "Remote sensing of forest degradation: a review," Environmental Research Letters, vol. 15, no. 10, Jun. 2020, Art. no. 103001.
D. Phiri, M. Simwanda, S. Salekin, V. R. Nyirenda, Y. Murayama, and M. Ranagalage, "Sentinel-2 Data for Land Cover/Use Mapping: A Review," Remote Sensing, vol. 12, no. 14, Jan. 2020, Art. no. 2291.
K. O. Abduraufovich, "Use of GIS Technologies and Satellite Data for Geological Research," Western European Journal of Modern Experiments and Scientific Methods, vol. 2, no. 11, pp. 24–30, Nov. 2024.
J. Wang, M. Bretz, M. A. A. Dewan, and M. A. Delavar, "Machine learning in modelling land-use and land cover-change (LULCC): Current status, challenges and prospects," Science of The Total Environment, vol. 822, May 2022, Art. no. 153559.
M. S. -Dastjerdi and A. Lak, "Towards resilient place emphasizing urban form: An assessment framework in urban design," Sustainable Cities and Society, vol. 96, Sep. 2023, Art. no. 104646.
C. Sothe et al., "A comparison of machine and deep-learning algorithms applied to multisource data for a subtropical forest area classification," International Journal of Remote Sensing, vol. 41, no. 5, pp. 1943–1969, Mar. 2020.
O. Okwuashi and C. E. Ndehedehe, "Deep support vector machine for hyperspectral image classification," Pattern Recognition, vol. 103, Jul. 2020, Art. no. 107298.
R. H. Topaloğlu, E. Sertel, and N. Musaoğlu, "Assessment of Classification Accuracies of Sentinel-2 and Landsat-8 data for Land Cover/Use Mapping," ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLI-B8, pp. 1055–1059, Jun. 2016.
R. N. Masolele, "Assessing land use following tropical deforestation : Combining remote sensing and deep learning," Ph.D. dissertation, Wageningen University, 2023.
A. Arfa and M. Minaei, "Utilizing multitemporal indices and spectral bands of Sentinel-2 to enhance land use and land cover classification with random forest and support vector machine," Advances in Space Research, vol. 74, no. 11, pp. 5580–5590, Dec. 2024.
A. Tariq, J. Yan, A. S. Gagnon, M. Riaz Khan, and F. Mumtaz, "Mapping of cropland, cropping patterns and crop types by combining optical remote sensing images with decision tree classifier and random forest," Geo-spatial Information Science, vol. 26, no. 3, pp. 302–320, Jul. 2023.
C. Brown, S. Sjögersten, M. J. Ledger, F. Parish, and D. Boyd, "Remote Sensing for Restoration Change Monitoring in Tropical Peat Swamp Forests in Malaysia," Remote Sensing, vol. 16, no. 15, Jan. 2024, Art. no. 2690.
P. S. Nagendram, P. Satyanarayana, and P. R. Teja, "Mapping Paddy Cropland in Guntur District using Machine Learning and Google Earth Engine utilizing Images from Sentinel-1 and Sentinel-2," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12427–12432, Dec. 2023.
"Replication package for land cover classification study," Google Earth Engine Code Repository. https://code.earthengine.google.com/8fae384fe296584613c96049f3cd15d3.
Downloads
How to Cite
License
Copyright (c) 2025 Dwi Ahmad Dzulhijjah, Kusrini, Rodrigo Martinez-Bejar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
