Volume 4, Issue 2 (9-2025)
jfer 2025, 4(2): 88-102 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Amiri Z, Abbasi M, Kahyani S, Riyahi Bakhtyari H R. (2025). Evaluating the Role of Spectral Library–Derived Indices in Improving Forest Type Classification in the Central Zagros Using Sentinel-2 Imagery. jfer. 4(2), : 7
URL: http://yujs.yu.ac.ir/jzfr/article-1-150-en.html
URL: http://yujs.yu.ac.ir/jzfr/article-1-150-en.html
Shahrekord University , hriyahi@sku.ac.ir
Abstract: (294 Views)
Background and objectives: The Zagros forests, one of Iran's natural ecosystems, possess significant ecological diversity, and understanding their typology is crucial for sustainable management. The forests of Flard County in Chaharmahal and Bakhtiari Province, primarily covered by oak (Quercus brantii) and pistachio (Pistacia mutica), are part of the central Zagros region. These forests play a prominent role in ecological sustainability, biodiversity conservation, and providing environmental services. However, the lack of current and accurate typological maps has hindered their scientific management. Traditional ground-based survey methods are inefficient due to high costs and difficult terrain. This study aimed to use modern remote sensing technologies and evaluate how spectral indices derived from a spectral library improve the accuracy of supervised classification of Sentinel-2 satellite imagery for discriminating forest types.
Materials and methods: To investigate the impact of spectral indices derived from the spectral library on distinguishing the region's dominant species, this study was conducted in three forest areas: two pure types and one mixed type. These areas were Mishan (pure oak), Kate-Siah (pure pistachio), and Vandun (mixed oak-pistachio cover) in Flard County, Chaharmahal and Bakhtiari Province. Three different classification scenarios were used. In Scenario 1, only Sentinel-2 images from October 15, 2024, were classified for all three study areas. In Scenario 2, in addition to the sensor's main bands, general spectral indices—NDVI, SAVI, MSAVI, GNDVI, and EVI—were applied to the Sentinel-2 data and incorporated into the classification process. These indices, respectively, assess greenness, reduce soil background effects, measure chlorophyll health, and enhance sensitivity to dense canopies. In Scenario 3, besides the main bands, specialized spectral indices—PRI, CRI, MCRI, CAI, NDVI800, NPCI, RENDVI, and ARI—extracted from the spectral library data of the oak and pistachio species were included in the classification process. Data classification in all three areas was performed using three supervised algorithms: Support Vector Machine (SVM), Maximum Likelihood Classification (MLC), and Minimum Distance (MinDist).
Accuracy was assessed using a ground truth map, the Kappa coefficient, and overall accuracy criteria.
Results: Results indicated that in Scenario 1, the Maximum Likelihood Classification (MLC) algorithm performed best with overall accuracies and Kappa coefficients of 98.4% and 0.71 in Mishan, 77.5% and 0.32 in Kate-Siah, and 86.7% and 0.67 in Vandun, respectively. In Scenario 2, the same algorithm was best in Mishan (97.7% overall accuracy, 0.65 Kappa coefficient) and Kate-Siah (75.9% overall accuracy, 0.38 Kappa coefficient). However, in Vandun, the SVM algorithm was superior, achieving an overall accuracy of 77.9% and a Kappa coefficient of 0.57. In Scenario 3, accuracy assessment results demonstrated that the SVM algorithm reported the highest accuracy in all three regions: Mishan (99.2% overall accuracy, 0.81 Kappa coefficient), Kate-Siah (98.2% overall accuracy, 0.74 Kappa coefficient), and Vandun (89.0% overall accuracy, 0.67 Kappa coefficient). A comparison of the three scenarios showed that specialized spectral indices derived from the spectral library were more effective in increasing classification accuracy than general indices. Despite the high accuracy of the algorithms, limitations such as spectral similarity between soil and vegetation in low-density areas affected the results.
Conclusion: Based on these findings, integrating valid spectral data with machine learning algorithms is an effective tool for preparing detailed forest cover maps. Using a spectral library alongside Sentinel-2 imagery enables more accurate discrimination of forest. The SVM algorithm is a suitable option for classifying forest types in areas with dense cover and complex structures. The findings of this research are applicable to conservation-management planning and the continuous monitoring of Zagros Forest ecosystems.
Materials and methods: To investigate the impact of spectral indices derived from the spectral library on distinguishing the region's dominant species, this study was conducted in three forest areas: two pure types and one mixed type. These areas were Mishan (pure oak), Kate-Siah (pure pistachio), and Vandun (mixed oak-pistachio cover) in Flard County, Chaharmahal and Bakhtiari Province. Three different classification scenarios were used. In Scenario 1, only Sentinel-2 images from October 15, 2024, were classified for all three study areas. In Scenario 2, in addition to the sensor's main bands, general spectral indices—NDVI, SAVI, MSAVI, GNDVI, and EVI—were applied to the Sentinel-2 data and incorporated into the classification process. These indices, respectively, assess greenness, reduce soil background effects, measure chlorophyll health, and enhance sensitivity to dense canopies. In Scenario 3, besides the main bands, specialized spectral indices—PRI, CRI, MCRI, CAI, NDVI800, NPCI, RENDVI, and ARI—extracted from the spectral library data of the oak and pistachio species were included in the classification process. Data classification in all three areas was performed using three supervised algorithms: Support Vector Machine (SVM), Maximum Likelihood Classification (MLC), and Minimum Distance (MinDist).
Accuracy was assessed using a ground truth map, the Kappa coefficient, and overall accuracy criteria.
Results: Results indicated that in Scenario 1, the Maximum Likelihood Classification (MLC) algorithm performed best with overall accuracies and Kappa coefficients of 98.4% and 0.71 in Mishan, 77.5% and 0.32 in Kate-Siah, and 86.7% and 0.67 in Vandun, respectively. In Scenario 2, the same algorithm was best in Mishan (97.7% overall accuracy, 0.65 Kappa coefficient) and Kate-Siah (75.9% overall accuracy, 0.38 Kappa coefficient). However, in Vandun, the SVM algorithm was superior, achieving an overall accuracy of 77.9% and a Kappa coefficient of 0.57. In Scenario 3, accuracy assessment results demonstrated that the SVM algorithm reported the highest accuracy in all three regions: Mishan (99.2% overall accuracy, 0.81 Kappa coefficient), Kate-Siah (98.2% overall accuracy, 0.74 Kappa coefficient), and Vandun (89.0% overall accuracy, 0.67 Kappa coefficient). A comparison of the three scenarios showed that specialized spectral indices derived from the spectral library were more effective in increasing classification accuracy than general indices. Despite the high accuracy of the algorithms, limitations such as spectral similarity between soil and vegetation in low-density areas affected the results.
Conclusion: Based on these findings, integrating valid spectral data with machine learning algorithms is an effective tool for preparing detailed forest cover maps. Using a spectral library alongside Sentinel-2 imagery enables more accurate discrimination of forest. The SVM algorithm is a suitable option for classifying forest types in areas with dense cover and complex structures. The findings of this research are applicable to conservation-management planning and the continuous monitoring of Zagros Forest ecosystems.
Article number: 7
Keywords: Falard forests, Forest type, Machine learning algorithms, Pistacia mutica, Quercus brantii, Sentinel‑2, Spectral library
References
1. Abbasi, M., Darvishsefat, A.A., Shepman, M.A., Marvi-Mohajer, M.R. & Sobhani, H. 2009. Spectral reflectance differences of leaves of major tree species in Caspian forests using ground spectrometry. Iranian Journal of Forest and Poplar Research, 4: 568-580.
2. Abedi, R. & Bonyad, A.A. 2013. Mapping tree species composition using satellite imagery. National Geomatics Conference, 1 May 2013, Tehran. Iran.
3. Ahmadi Sani, N., Darvishsefat, A.A., Zobeiri, M., Farzaneh, A., 2009. Potentiality of ASTER images for forest density mapping in Zagros (Case study: Marivan forests). Iranian Journal of Natural Resources 61(4): 603-614.
4. Amini, M. 2006. Monitoring forest extent changes and its relation with physiographic and human factors using satellite imagery and GIS (Case study: Aramardeh forests, Baneh). M.Sc. Thesis, Gorgan University of Agricultural Sciences and Natural Resources, Iran.
5. Amiri, M., Mostafa, M. & Rahimi, M. 2019. Mapping forest types in Ziarat-Gorgan forest management plan using parametric and non-parametric methods. Iranian Journal of Forest, 2: 239-254.
6. Cho, M.A., Malahlela, O. & Ramoelo, A. 2015. Assessing the utility of World View-2 imagery for tree species mapping in South African subtropical humid forest. International Journal of Applied Earth Observation and Geoinformation, 38: 349-357. [DOI:10.1016/j.jag.2015.01.015]
7. Ebrahimi, G. 2012. Forest type mapping using satellite data (Case study: part of Marivan forests).
8. M.Sc. Thesis, Kurdistan University, Iran.
9. Ginindza, Th. 2025. Identification of commercial forest tree species using Sentinel‑2 and PlanetScope imageries in the Usutu Forest, Eswatini. Journal of Geographic Information System, 17: 1-22. [DOI:10.4236/jgis.2025.171001]
10. Grabska, E., Hostert, P., Pflugmacher, D. & Ostapowicz, K. 2019. Forest stand species mapping using the Sentinel‑2 time series. Remote Sensing, 11: 1197. [DOI:10.3390/rs11101197]
11. Hadiyan, J., Shataei, S. & Bonyad, A. 2012. Evaluation of vegetation indices for forest canopy density estimation. Iranian Journal of Forest and Poplar Research, 20: 33-45.
12. Hościło, A. & Lewandowska, A. 2019. Mapping forest type and tree species on a regional scale using multi-temporal Sentinel‑2 data. Remote Sensing, 11: 929. [DOI:10.3390/rs11080929]
13. Isbaex, C., Coelho, A., Gonçalves, A. & Sousa, A. 2024. Mapping of forest species using Sentinel‑2A images in the Alentejo and Algarve Regions, Portugal. Land, 13: 2-21. [DOI:10.3390/land13122184]
14. Jeong, J. & Park, Ch. 2023. Developing a mapping procedure for urban forests using online map services and Sentinel‑2A images. Urban Forestry & Urban Greening, 89: 128095. [DOI:10.1016/j.ufug.2023.128095]
15. Laurin, G.V., Puletti, N., Hawthorne, W., Liesenberg, V., Corona, P., Papale, D. & Valentini, R. 2016. Discrimination of tropical forest types and dominant species using hyperspectral and simulated Sentinel‑2 data. Remote Sensing of Environment, 176: 163-176. [DOI:10.1016/j.rse.2016.01.017]
16. Luhrabi, Y., Abbasi, M., Soltani, A., Riyahi bakhtyari, H.R. 2018. Determination of the most suitable method for forest type mapping in central Zagros using landsat-8 satellite Images, Journal of Forest Research and Development, 4(2): 191-205.
17. Mirki, M., Sohrabi, H., Sadeghi, S., Fatehi, P. & Immitzaer, M. 2023. Mapping mangrove forests using Sentinel‑2 imagery and Google Earth Engine. Marine Science and Technology Journal, 22: 40-49.
18. Mohammadpour, P., Viegas, D. & Viegas, C. 2022. Vegetation mapping with Random Forest using Sentinel‑2 and GLCM texture features. Remote Sensing, 14: 2-20. [DOI:10.3390/rs14184585]
19. Nasiri, V., Beloiu, M., Darvishsefat, A.A., Griess, V., Maftei, C. & Waser, L. 2022. Mapping tree species composition in a Caspian temperate mixed forest using spectral-temporal metrics and machine learning. International Journal of Applied Earth Observation and Geoinformation, 116: 103154. [DOI:10.1016/j.jag.2022.103154]
20. Pourghasemi, M. 2021. Radiative transfer models at leaf and canopy of trees for two species of Quercus brantii and Pistacia atlantica in Zagros forests (Case study: Chaharmal-Bakhtiyari province). PhD Thesis, Shahrekord University, Iran, 145p.
21. Yang, J., Kyung Lee, Y. & Chi, J. 2023. Spectral unmixing-based Arctic plant species analysis using a spectral library and terrestrial hyperspectral imagery. International Journal of Applied Earth Observation and Geoinformation, 125: 103583. [DOI:10.1016/j.jag.2023.103583]
22. Zarco‐Tejada, P J., Ustin, S.L., & Whiting, M.L. 2005. Temporal and spatial relationships between within‐field yield variability in cotton and high‐spatial hyperspectral remote sensing imagery. Agronomy journal, 97(3): 641-653. [DOI:10.2134/agronj2003.0257]
23. Zhang, J., Wang, Ch., Yuan, L., Zang, Y. & Wu, K. 2020. Construction of a plant spectral library based on an optimized feature selection method. Biosystems Engineering, 195: 1-16. [DOI:10.1016/j.biosystemseng.2020.04.008]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
