Using machine learning algorithms, Landsat 8 and Sentinel 2 satellite imagery for estimating forest canopy density of Zagros Forests

Abbasiwand, Ahmad; Sohrabi, Hormoz; Miraki, Mojdeh

[Home ] [Archive]

[ فارسی ]

Journal of Geomatics Science and Technology

Main Menu

Home

Browse

Journal Info

Guide for Authors

Submit Manuscript

Articles archive

For Reviewers

Contact us

Site Facilities

Reviewers

Search in website

Receive site information

Volume 15, Issue 1 (9-2025)

JGST 2025, 15(1): 27-36

Back to browse issues page

Using machine learning algorithms, Landsat 8 and Sentinel 2 satellite imagery for estimating forest canopy density of Zagros Forests

Ahmad Abbasiwand

, Hormoz Sohrabi ^*

, Mojdeh Miraki

Abstract: (130 Views)

The significance of canopy cover as a crucial variable in assessing, monitoring, and managing the Zagros forests cannot be overstated. Since canopy cover reflects various ecological changes, forest managers and related institutions require accurate and up-to-date maps and data to enhance forest management efforts. The integration of satellite imagery and machine learning models has significantly improved our understanding of forest ecosystems, enabling the development of effective conservation strategies and the prevention of resource depletion. This study utilized imagery from the Sentinel-2 and Landsat 8 satellites, employing machine learning models to analyze canopy cover in the Zagros forests. Five algorithms were tested: Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVR), Multivariate Adaptive Regression Splines (MARS), and Artificial Neural Networks (ANN). To evaluate these models, 2,631 plots (each 400 meters in size) across 27 forest areas were selected, and canopy cover percentages were calculated. The results showed that using Landsat 8 imagery, the most effective models were MARS (63.7%), RF (62.7%), and ANN (61.7%), based on adjusted coefficient of determination values. With Sentinel-2 imagery, the best-performing models were MARS (73.7%), SVR (72.7%), and RF (71.7%). Comparatively, Sentinel-2 produced superior results, with its highest accuracy (73.7%) exceeding the best result from Landsat 8 (63.7%). Overall, canopy cover modeling across the Zagros forests indicated that the Random Forest algorithm (73.7%) outperformed other methods. Additionally, Sentinel-2 imagery proved more efficient than Landsat 8, demonstrating approximately 7% higher accuracy in estimating canopy cover. The ability to analyze and map canopy cover using satellite imagery and advanced machine learning models provides forest managers with cost-effective and reliable tools for making informed decisions regarding conservation and sustainable forest management.

Article number: 2

Keywords: Forest monitoring, plant indices, random forest, canopy cover

Full-Text [PDF 1025 kb] (72 Downloads)

Type of Study: Research | Subject: GIS
Received: 2024/11/28

References

1. A. Safari and H. Sohrabi, "Effect of climate change and local management on aboveground carbon dynamics (1987-2015) in Zagros oak forests using Landsat time-series imagery," Appl. Geogr., vol. 110, no. July, p. 102048, 2019, doi: 10.1016/j.apgeog.2019.102048. [DOI:10.1016/j.apgeog.2019.102048]

2. F. Pordel, A. Ebrahimi, and Z. Azizi, "Canopy cover or remotely sensed vegetation index, explanatory variables of above-ground biomass in an arid rangeland, Iran," J. Arid Land, vol. 10, no. 5, pp. 767-780, Oct. 2018, doi: 10.1007/s40333-018-0017-y. [DOI:10.1007/s40333-018-0017-y]

3. Z. Azizi, A. Najafi, and H. Sohrabi, "Forest Canopy Density Estimating , Using Satellite Images," in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Beijing, China, 2008, p. 4. doi: 10.13140/2.1.2953.6967.

4. A. Ildoromi, F. Ghasemi, and N. Bahmani, "Investigation of the Role of Socio-Economic Factors on the Degradation of Zagros Forests (Kakareza Lorestan)," Iran. J. For. Range Prot. Res., vol. 13, no. 2, pp. 140-149, 2016, doi: 10.22092/ijfrpr.2016.106021.

5. H. Beygiheidarlou and et al., "Forest Cover Density Mapping of Zagros Forests Using Landsat-9 Imagery and Hemispherical Photographs," For. Res. Dev., vol. 9, no. 1, pp. 47-65, 2023, doi: 10.30466/jfrd.2023.54591.1661.

6. A. Anand, S. K. Singh, and S. Kanga, "Estimating the Change in Forest Cover Density and Predicting NDVI for West Singhbhum Using Linear Regression," Int. J. Environ. Rehabil. Conserv., vol. 9, pp. 193-203, 2018. [DOI:10.31786/09756272.18.9.1.125]

7. S. Vafaei et al., "Improving accuracy estimation of Forest Aboveground Biomass based on incorporation of ALOS-2 PALSAR-2 and Sentinel-2A imagery and machine learning: A case study of the Hyrcanian forest area (Iran)," Remote Sens., vol. 10, no. 2, 2018, doi: 10.3390/rs10020172. [DOI:10.3390/rs10020172]

8. T. N. Phan, V. Kuch, and L. W. Lehnert, "Land Cover Classification Using Google Earth Engine and Random Forest Classifier: The Role of Image Composition," Remote Sens., vol. 12, no. 15, p. 2411, 2020. [DOI:10.3390/rs12152411]

9. H. Panahi, Z. Azizi, H. Kiadaliri, S. A. Almodaresi, and H. Aghamohamadi, "Bare soil detecting algorithms in western iran woodlands using remote sensing," Smart Agric. Technol., vol. 7, no. March, pp. 1-9, 2024, doi: 10.1016/j.atech.2024.100429. [DOI:10.1016/j.atech.2024.100429]

10. M. Taefi Feijani, S. Azadnejad, and M. Moradi, "Improvement of the Forest Canopy Density Model Based on the Addition of the FCC Index and the Average Kernel Implementation," Sp. Sci. Technol., vol. 14, no. 2, pp. 27-36, 2021, doi: 10.22034/jsst.2021.1191.

11. S. Vafaei and et al., "Estimation of Forest Canopy Using Remote Sensing and Geostatistics (Case Study: Marivan Baghan Forests)," J. Environ. Sci. Technol., vol. 24, no. 1, pp. 71-82, 2022, doi: 10.30495/jest.2018.20376.294.

12. A. Dabija and et al., "Comparison of Support Vector Machines and Random Forests for Corine Land Cover Mapping," Remote Sens., vol. 13, p. 777, 2021, doi: 10.3390/rs13040777. [DOI:10.3390/rs13040777]

13. R. K. M. Malhi et al., "Synergistic evaluation of Sentinel 1 and 2 for biomass estimation in a tropical forest of India," Adv. Sp. Res., vol. 69, no. 4, pp. 1752-1767, Feb. 2022, doi: 10.1016/j.asr.2021.03.035. [DOI:10.1016/j.asr.2021.03.035]

14. R. A. Parma and S. Shataey, "Capability Study on Mapping the Diversity and Canopy Cover Density in Zagros Forests Using ETM+ Images (Case Study: Ghalajeh Forests, Kirmanshah Province)," Iran. J. For., vol. 2, no. 3, pp. 231-242, 2010.

15. M. Ghanbari Motlagh and et al., "Investigating Spatiotemporal Changes in Greenness of Zagros Oak Forests in Response to Drought," J. Renew. Nat. Resour. Res., vol. 13, no. 2, pp. 131-143, 2023, doi: 10.30495/jrnr.2023.71340.10281.

16. H. Naghavi, "Application of Quickbird Satellite Images in Estimating the Canopy Level of Zagros Forests (Case Study: Gol Khorramabad Castle Area)," Sari University of Agricultural Sciences and Natural Resources, 2014.

17. A. Safari and H. Sohrabi, "Ability of Landsat-8 OLI derived texture metrics in estimating aboveground carbon stocks of coppice Oak Forests.," Int. Arch. Photogramm. Remote Sens. & Spat. Inf. Sci., vol. 41, 2016. [DOI:10.5194/isprs-archives-XLI-B8-751-2016]

18. M. Miraki, H. Sohrabi, P. Fatehi, and M. Kneubuehler, "Comparison of Machine Learning Algorithms for Broad Leaf Species Classification Using UAV-RGB Images," J. Geomatics Sci. Technol., vol. 10, no. 2, pp. 1-10, 2020.

19. N. Nazariani and A. Fallah, "Investigation of the Effect of Main and Artificial Bands of Sentinel-2 Satellite Images on Estimation of Quantitative Characteristics of Zagros Forests," Sci. Q. Geogr. Data, vol. 31, no. 124, pp. 103-118, 2023, doi: 10.22131/sepehr.2023.553505.2875.

20. A. Safari and H. Sohrabi, "The effect of digital preprocessing and modeling method on an estimation of aboveground carbon stock of Zagros forests using Landsat 8 imagery," RS GIS Nat. Resour., vol. 9, no. 4, pp. 73-89, 2019.

21. S. Arekhi and M. Adibnejad, "Efficiency Assessment of the Support Vector Machines for Land Use Classification Using Landsat ETM+ Data (Case Study: Ilam Dam Catchment)," Iran. J. Range Desert Res., vol. 18, no. 3, pp. 420-440, 2011, doi: 10.22092/ijrdr.2011.102175.

22. R. M. Adnan, Z. Liang, and S. Heddam, "Least Square Support Vector Machine and Multivariate Adaptive Regression Splines for Streamflow Prediction in Mountainous Basin Using Hydro-Meteorological Data as Inputs," J. Hydrol., vol. 124, p. 371, 2019, doi: 10.1016/J.JHYDROL.2019.124371. [DOI:10.1016/j.jhydrol.2019.124371]

23. N. Busto Serrano, A. Suárez Sánchez, and F. Sánchez Lasheras, "Identification of Gender Differences in the Factors Influencing Shoulders, Neck, and Upper Limb MSD by Means of Multivariate Adaptive Regression Splines (MARS)," Appl. Ergon., vol. 82, p. 102981, 2020, doi: 10.1016/j.apergo.2019.102981. [DOI:10.1016/j.apergo.2019.102981]

24. C. Witharana and H. J. Lynch, "An Object-Based Image Analysis Approach for Detecting Penguin Guano in Very High Spatial Resolution Satellite Images," Remote Sens., vol. 8, no. 5, p. 375, 2016. [DOI:10.3390/rs8050375]

25. X. Huang and et al., "Comparative Study on Remote Sensing Methods for Forest Height Mapping in Complex Mountainous Environments," Remote Sens., vol. 15, p. 2275, 2023, doi: 10.3390/rs15092275. [DOI:10.3390/rs15092275]

Send email to the article author

Add your comments about this article

Mendeley

Zotero

RefWorks

Abbasiwand A, Sohrabi H, Miraki M. Using machine learning algorithms, Landsat 8 and Sentinel 2 satellite imagery for estimating forest canopy density of Zagros Forests. JGST 2025; 15 (1) : 2
URL: http://jgst.issgeac.ir/article-1-1208-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 15, Issue 1 (9-2025)

Back to browse issues page