Document Type : Research Paper

Authors

1 Assistant Professor of Remote Sensing, Geoinformatics Department, Faculty of Geographical Sciences, Kharazmi University, Tehran, Iran

2 Ph.D. Student, Department of Forestry and Forest Economics, Faculty of Natural Resources, University of Tehran, Karaj, Iran

10.22092/ijrdr.2026.136590

Abstract

Background and Objective:
Accurate monitoring of rangeland vegetation is crucial for ecosystem management, biodiversity conservation, and global food security. Hyperspectral remote sensing, by capturing information across hundreds of narrow spectral bands, provides a powerful tool for discriminating vegetation types at the species level. The objective of this study is to evaluate the capability of the EO-1 Hyperion hyperspectral sensor in identifying and discriminating four dominant rangeland plant species (Agropyron intermedium, Medicago sativa L., Peganum harmala L., and Achillea filipendulina Lam.) in the Ghotour region of Khoy County, Iran.
Materials and Methods:
A Hyperion hyperspectral image acquired on 20 June 2010 over the Ghotour region was used in this study. Data preprocessing included radiometric correction through the removal of noisy and low-quality bands and striping artifacts, atmospheric correction using the FLAASH algorithm to convert radiance to surface reflectance, and geometric and topographic correction using 23 ground control points. To reduce data dimensionality, the Minimum Noise Fraction (MNF) transformation was applied. The purest vegetation pixels were then extracted using the Pixel Purity Index (PPI), and corresponding spectral signatures were collected based on field observations. Subsequently, the extracted spectra were analyzed and classified using the Spectral Angle Mapper (SAM) and Spectral Information Divergence (SID) algorithms. Classification accuracy was evaluated using 54 independent ground control points.
Results:
The results indicated that the SAM algorithm outperformed SID, achieving an overall accuracy of 70% and a Kappa coefficient of 0.57, compared to 64% overall accuracy and a Kappa coefficient of 0.49 for SID. This superiority highlights the greater capability of SAM in identifying pure species pixels under complex field conditions. The highest classification accuracy was obtained for the Agropyron intermedium class, whereas the lowest accuracy was observed for Achillea filipendulina Lam., primarily due to spectral mixing effects. Moreover, the greatest spectral confusion occurred between Peganum harmala L. and Achillea filipendulina Lam..
Conclusion:
The integration of Hyperion hyperspectral data with rigorous preprocessing, advanced spectral analysis, and angle-based classification algorithms such as SAM provides an effective framework for discriminating rangeland vegetation species in heterogeneous mountainous environments. Although the spatial resolution of Hyperion imposes moderate limitations for small shrub species, the applied processing chain substantially enhances classification accuracy.

Keywords

  • Aghababaei, M., Ebrahimi, A., Naghipour, A. A., Asadi, E., & Verrelst, J. (2021). Vegetation types mapping using multi-temporal Landsat images in the Google Earth Engine platform. Remote Sensing, 13(22), 4683. https://doi.org/10.3390/rs13224683
  • Akbari, D., Safari, A., Khazaei, S., & Homayouni, S. (2015). Improving spectral–spatial classification of minimum forest cover using dimensionality reduction of hyperspectral images. Journal of Geomatics Science and Technology, 5(2), 219–229. (In Persian)
  • Amigo, J. M., Babamoradi, H., & Elcoroaristizabal, S. (2015). Hyperspectral image analysis: A tutorial. Analytica Chimica Acta, 896, 34–51. https://doi.org/10.1016/j.aca.2015.09.030
  • Arghavanian, A., Dorvishzadeh, R., Rasa, I., & Hoseini Asl, A. (2011). Extraction of potential gold areas in the western Meshgin Shahr region using Hyperion images. Iranian Journal of Remote Sensing & GIS, 3(1). (In Persian)
  • Belvasi, M., Asghari Saraskanroud, S., Zeinali, B., & Sahebi Vayghan, S. (2015). Exploration of potential copper areas in Khoy City (Ghezel Dash) using Hyperion images. Researches in Physical Geography, 47(2), 287–302. (In Persian)
  • Boardman, J. W., Kruse, F. A., & Green, R. O. (1995). Mapping target signatures via partial unmixing of AVIRIS data. In Summaries of the Fifth Annual JPL Airborne Earth Science Workshop (Vol. 1).
  • Boardman, J. W., & Kruse, F. A. (2011). Analysis of imaging spectrometer data using n-dimensional geometry and a mixture-tuned matched filtering approach. IEEE Transactions on Geoscience and Remote Sensing, 49(11), 4138–4152. https://doi.org/10.1109/TGRS.2011.2161585
  • Chaudhry, F., Wu, C., Liu, W., Chang, C., & Plaza, A. J. (2006). Pixel purity index-based algorithms for endmember extraction from hyperspectral imagery.
  • Chen, B., Liu, L., Zou, Z., & Shi, Z. (2023). Target detection in hyperspectral remote sensing images: Current status and challenges. Remote Sensing, 15(13), 3223. https://doi.org/10.3390/rs15133223
  • Christian, B., & Krishnayya, N. S. R. (2009). Classification of tropical trees using Hyperion (EO-1) and SAM algorithm. Current Science, 1601–1607.
  • Fahimnejad, H., Soofbaf, S. R., Alimadadi, A., Valdanzouj, M. J., & Rezaei, Y. (2007). Crop type discrimination using hyperspectral data. In Proceedings of Geomatic Conference 86 (In Persian).
  • García-Vera, Y. E., Polochè-Arango, A., Mendivelso-Fajardo, C. A., & Gutiérrez-Bernal, F. J. (2024). Hyperspectral image analysis and machine learning techniques for crop disease detection: A review. Sustainability, 16(14), 6064. https://doi.org/10.3390/su16146064
  • Ghamisi, P., Plaza, J., Chen, Y., Li, J., & Plaza, A. J. (2017). Advanced spectral classifiers for hyperspectral images: A review. IEEE Geoscience and Remote Sensing Magazine, 5(1), 8–32. https://doi.org/10.1109/MGRS.2016.2616418
  • Ghanaei Qoshkhaneh, N., & Golzarian, M. R. (2014). Application of hyperspectral imaging in quality assessment of agricultural products. National Conference on New Technologies in Harvesting and Postharvest of Agricultural Products. (In Persian)
  • Green, A. A., Berman, M., Switzer, P., & Craig, M. D. (1988). A transformation for ordering multispectral data in terms of image quality. IEEE Transactions on Geoscience and Remote Sensing, 26(1), 65–74. https://doi.org/10.1109/36.3001
  • Hennessy, A., Clarke, K., & Lewis, M. (2020). Hyperspectral classification of plants: A review of waveband selection generalisability. Remote Sensing, 12(1), 113.‏ https://doi.org/10.3390/rs12010113
  • Khazaei, S., Homayooni, S., & Safari, A. R. (2011). Hyperspectral imagery and CC&D considerations against its threats. Journal of New Defense Technologies, 1(2), 63–74. (In Persian). https://dor.isc.ac/dor/20.1001.1.26762935.1389.1.2.7.8
  • Kruse, F. A. (2004, March). Comparison of ATREM, ACORN, and FLAASH atmospheric corrections using low-altitude AVIRIS data of Boulder, CO. In Summaries of 13th JPL Airborne Geoscience Workshop, Jet Propulsion Lab, Pasadena, CA (pp. 1-10).‏
  • Lim, J., Kim, K. M., & Jin, R. (2019). Tree species classification using hyperion and sentinel-2 data with machine learning in South Korea and China. ISPRS International Journal of Geo-Information, 8(3), 150.‏ https://doi.org/10.3390/ijgi8030150
  • Minu, S., & Shetty, A. (2015). Atmospheric correction algorithms for hyperspectral imageries: A review. International Research Journal of Earth Sciences, 3(5), 14-18.‏
  • Najibzadeh, M., Fayyaz, M., & Pezeshki, M. H. (2016). Preparation of the distribution map of medicinal plants based on the natural geographical zoning in West Azerbaijan Province. National Conference on Medicinal, Aromatic and Spice Plants. SID. (In Persian).
  • NV5 Geospatial. (n.d.). Pixel Purity Index (PPI). Retrieved [date you accessed the page], from https://www.nv5geospatialsoftware.com/docs/PixelPurityIndex.html
  • Pascucci, S., Pignatti, S., Casa, R., Darvishzadeh, R., & Huang, W. (Eds.). (2021). Hyperspectral remote sensing of agriculture and vegetation. MDPI.‏
  • Poormirzaee, R., & Mohammadi Moskouei, M. (2012). Topographic correction of hyperspectral data of west east-Azarbayjan. Journal of Mining Engineering, 7(15), 25–33. https://dor.isc.ac/dor/20.1001.1.17357616.1391.7.15.3.1
  • Pu, R. (2017). Hyperspectral remote sensing: Fundamentals and practices. CRC Press. https://doi.org/10.1201/9781315120607
  • Tong, Q., Xue, Y., & Zhang, L. (2014). Progress in hyperspectral remote sensing science and technology in China. IEEE JSTARS, 7(1), 70–91. https://doi.org/10.1109/JSTARS.2013.2267204
  • Rabiei, M. (2015). Identification of rangeland plants. Tehran: Payam Noor University, Faculty of Agricultural Sciences. (In Persian).
  • Salehi Ardali, S., Iravani, M., & Senn, J. (2014). Effect of short-term exclusion on forage production. Iranian Journal of Applied Ecology, 2(5), 65–76. (In Persian)
  • Shahnavazi, A. (2021). Alfalfa cultivation profitability. Extension Journal of Forage and Animal Feed, 1(2), 33–42. (In Persian)
  • Singh, D., & Singh, R. (2015). Evaluation of EO-1 Hyperion data for crop studies. Advances in Remote Sensing, 4(4), 263. https://doi.org/10.4236/ars.2015.44021
  • Thenkabail, P. S., Lyon, J. G., & Huete, A. (2018). Advances in hyperspectral remote sensing of vegetation and agricultural crops. In Fundamentals, sensor systems, spectral libraries, and data mining for vegetation (pp. 3-37). CRC press.
  • S. Geological Survey. (n.d.). EO-1 sensors. Earth Resources Observation and Science (EROS) Center. Retrieved September 28, 2025, from https://www.usgs.gov/centers/eros/eo-1-sensors
  • Valizadeh, M. (2018). Optimization of tissue culture of the medicinal plant Peganum harmala. Journal of Plant Physiology and Breeding, 8(1), 101–109.
  • Yazdani, E., & Tarahi, A. A. (2015). Evaluation of supervised classification algorithms for mapping rice cultivation areas using Hyperion hyperspectral images. In Proceedings of the First International Congress on Earth, Space, and Clean Energy (Ardabil, Iran). (In Persian) Retrieved from https://civilica.com/doc/456770
  • Yousefi Khanqah, S., Razmjooei, D., Dehdari, S., & Arman, N. (2018). Mapping rangeland vegetation types using different satellite image classification algorithms. Rangeland and Watershed Management, 3(Fall), 847–856. (In Persian).
  • Zaka, M. M., & Samat, A. (2024). Advances in remote sensing and machine learning for invasive plants. Remote Sensing, 16, 3781. https://doi.org/10.3390/rs16203781
  • Zare Chahouki, M. A., Mashgholi, M., & Hossein Jafari, S. (2015). Classification of vegetation cover related to environmental factors. Plant Research, 28(5), 995–1005. (In Persian)
  • Zulfa, A. W., Norizah, K., Hamdan, O., Faridah-Hanum, I., Rhyma, P. P., & Fitrianto, A. (2021). Spectral signature analysis of mangrove species. Ecological Indicators, 130, 108148. https://doi.org/10.1016/j.ecolind.2021.108148