Zoning of Forest Stands Susceptible to Oak Decline in the Zagros Region Using Machine Learning Methods (Balot Boland forest Chaharmahal va Bakhtyari Province)

Ghafari, Sohrab; Riyahi Bakhtyari, Hamid Reza; Abbasi, Mozhgan

doi:10.22111/jneh.2024.47669.2017

Zoning of Forest Stands Susceptible to Oak Decline in the Zagros Region Using Machine Learning Methods (Balot Boland forest Chaharmahal va Bakhtyari Province)

Document Type : Research Article

Authors

¹ PhD student Department of Forest Science, Shahrekord University, Shahrekord, Iran

² Assistant Professor of Forest Science, Shahrekord University, Shahrekord, Iran

³ Associate Professor of Forest Science, Shahrekord University, Shahrekord, Iran

10.22111/jneh.2024.47669.2017

Abstract

Zagros forests are one of Iran’s most valuable ecosystems, hosting diverse fauna and flora. Recent crises such as global warming, droughts, and dust storms have endangered this ecosystem, causing the weakening of individual trees or groups of trees in the region. Decline is an important disorder and challenge that threatens oak trees in the Zagros region. This study aimed to investigate the possibility of zoning decline-affected trees using machine-learning algorithms. The study area encompasses 101 hectares of middle Zagros forests known as the "Baloot Boland" region. Filed sampling was conducted to assess the health status of trees in 37 sample plots (1000 square meters each). In addition, the ground truth map was prepared on a tree-by-tree investigation basis for 11% of the total area. After analyzing reparability, three classes were selected for classification: "Class 1" representing areas with decline levels below 50%, "Class 2" representing areas with drought levels exceeding 50%, and "Class 3" including bare soil, sparse forest, roads, and rocky outcrops. The capabilities of the four machine learning methods, namely Maximum Likelihood, Neural Network, Random Forest, and Support Vector Machine, were compared. The results showed that the Maximum Likelihood method provided the highest overall accuracy and Kappa coefficients of 87.0% and 73.0%, respectively. Additionally, in Class 2, the area of decline was higher, indicating an increasing level of decline in the region. It is recommended to study the spectral behavior of trees directly during the decline process and to introduce suitable spectral indices to identify the early stage of decline-affected stands.

Keywords

Main Subjects

Environmental Hazards

References

References (in Persian)

Abdollahi, H., & Shataee Joybari, S. (2012). Comparative evaluation of IRS-P6-LISS-III and LISS IV images for canopy cover mapping of Zagros forests (Case Study: Javanroud Forests). Journal of Wood and Forest Science and Technology, 19(1), 43-60. SID. https://sid.ir/paper/156857/en [In Persian]

Barazmand, S., Shataee Joybari, S., Abdi, O. (2012). Recognition possibility of tree canopy dieback using a high-resolution satellite image of Quick bird (Case study: Shastkolate forest, Gorgan). Iranian journal of forest and poplar research, 19: 466-477. [In Persian]

Barazmand, S., Shataee Joybari, S., Kavousi, M.R., & Habashi, H. (2012). Spatial distribution of tree crown dieback and its relation with some environmental factors and road network. Journal of Wood And Forest Science and Technology, 19(3), 159-174. SID. https://sid.ir/paper/156636/en [In Persian]

Pir Bavaghar, M. (2012). Evaluation of capability of irs-p6 satellite data for predicting quantitative attributes of forests (case study: northern Zagros forests). Iranian Journal of Forest, 3(4), 277-289. SID. https://sid.ir/paper/123193/en [In Persian]

Pilehvar, B., Veys Karami, GH.H., Taheri Abkenar, K., Sousani, J., & Akbari, H. (2010). Conservation priority setting of different vegetation types in off-reserve areas of Zagros forests, based on their diversity contained. Iranian Journal of Forest, 2(1), 81-91. SID. https://sid.ir/paper/123168/en [In Persian]

Jazirehi MH, Ebrahimi M. (2003). Silviculture in Zagros. Tehran: University of Tehran Press. p. 560. [In Persian]

Hosseini, A., hosseini, S.M., rahmani, A., & azadfar, D. (2013). Effect of tree mortality on the structure of Brant's oak (Quercus Brantii) forests of Ilam province of Iran. Iranian Journal of Forest and Poplar Research, 20(4 (50)), 565-577. SID. https://sid.ir/paper/111206/en [In Persian]

Heidari Naserabadi, S. (2016). Investigating the spatiotemporal distribution pattern of Iranian oak drying using remote sensing and GIS (study: Bashet region, Kohgiluyeh, and Boyer Ahmad provinces). MSc Thesis. Yasuj University. [In Persian]

Zakeri Anaraki, S., & Fallah Shamsi, S.R. (2014). An investigation on Persian Oak (Quercus brantii Lindl) single tree defoliation mapping, using Rapideye and Aster-L1B satellite imageries. Iranian Journal of Forest, 5(4), 443-456. SID. https://sid.ir/paper/715718/en [In Persian]

Fundamentals of applied remote sensing with emphasis on satellite image processing. Tabriz University Press. P. 806. [In Persian]

Alavipanah S.K. (2011). Fundamentals of modern remote sensing and photographic interpretation and aerial photography. University of Tehran. Press. 800p. [In Persian]

Lohrabi, 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. Forest Research and Development, 4(2 ), 191-205. SID. https://sid.ir/paper/263776/en [In Persian]

Marvie Mohajer. M.R. Silvclture. (2011). University of Tehran. Press. 418p [In Persian]

Mirzaei, J., Akbarinia, M., Hosseini, M., Tabari, M., & Jalali, G. (2008). Comparison of naturally regenerated woody species concerning physiographic and soil factors in Zagros forests (Case study: Arghavan reservoir in north of Ilam province). Pajouhesh va sazandegi, 20(4): 16-23. SID. https://sid.ir/paper/19869/en [In Persian]

Niyazi, Y., Malekinezhad, H., Ekhtesasi, M.R., Morshedi, J., & Hosseini, S.Z.A.A. (2011). Comparison between two classification methods of maximum likelihood and artificial neural network for providing land use maps case study: Ilam dam area. Geography and Development, 8(20), 119-132. SID. https://sid.ir/paper/77376/en [In Persian]

References (in English)

Boloorani, A.D., Ranjbareslamloo, S., Mirzaie, S., Bahrami, H.A., Mirzapour, F. & Tehrani, N.A. (2020). Spectral behavior of Persian oak under compound stress of water deficit and dust storm. International Journal of Applied Earth Observation and Geoinformation, 88, p.102082.

Bolstad, P. and Lillesand, T.M. (1991). Rapid maximum likelihood classification. Photogrammetric Engineering and Remote Sensing, 57(1), pp.67-74.

Campbell, J.B. & Hall-Beyer, M. (1997). [Introduction to remote sensing. Cartographica, 34(1), p.70.

Czerwinski, C. J., D. J. King, & Mitchell S.W. (2014). Mapping forest growth and decline in a temperate mixed forest using temporal trend analysis of Landsat imagery, 1987–2010, Remote Sensing of Environment, 141: 188 200.

Coluzzi, R., Fascetti, S., Imbrenda, V., Italiano, S.S.P., Ripullone, F. & Lanfredi, M. (2020). Exploring the use of sentinel-2 data to monitor heterogeneous effects of contextual drought and heatwaves on Mediterranean forests. Land, 9(9), p.325.

Dionisio, M.A., Alcaraz-Segura, D. & Cabello, J. (2012). Satellite-based monitoring of ecosystem functioning in protected areas: recent trends in the oak forests (Quercus Pyrenaica Willd.) of Sierra Nevada (Spain). International Perspectives on Global Environmental Change, 355, p.37.

EESA, (2019). User Guides - Sentinel-2 MSI - Level-2 Processing, https://sentinel.esa.int/web/sentinel/user-guides/sentinel-2-msi/processing-levels/level-2

Ekstrand, S. (1996). Landsat TM-based forest damage assessment: correction for topographic effects. Photogrammetric Engineering and Remote Sensing, 62(2), pp.151-162.

Franklin, S. E. (2001). Remote Sensing for Sustainable Forest Management. CRC Press, United States of America. pp 114-135

Gazol, A., Camarero, J.J., Vicente Serrano, S.M., Sánchez Salguero, R., Gutiérrez, E., de Luis, M., Sangüesa Barreda, G., Novak, K., Rozas, V., Tíscar, P.A. & Linares, J.C. (2018). Forest resilience to drought varies across biomes. Global change biology, 24(5), pp.2143-2158.

Hoffer, A., Swain, P.H. & Davis, S.M. (1978). Remote Sensing: The Quantitative Approach. Biological and Physical Considerations in Applying Computer-Aided Analysis Techniques to Remote Sensor Data, pp.227-289.

Hornero, A., Zarco-Tejada, P.J., Quero, J.L., North, P.R., Ruiz-Gómez, F.J., Sánchez-Cuesta, R. & Hernández-Clemente, R. (2021). Modeling hyperspectral-and thermal-based plant traits for the early detection of Phytophthora-induced symptoms in oak decline. Remote Sensing of Environment, 263, p.112570

Huang, K. & Xia, J. (2019). High ecosystem stability of evergreen broadleaf forests under severe droughts. Global Change Biology, 25(10), pp.3494-3503.

Huete, A.R. (1988). A soil-adjusted vegetation index (SAVI). Remote sensing of environment, 25(3), pp.295-309.

Italiano, S.S., Camarero, J.J., Borghetti, M., Colangelo, M., Pizarro, M. & Ripullone, F. (2023). Radial growth, wood anatomical traits, and remote sensing indexes reflect different impacts of drought on Mediterranean forests. Forest Ecology and Management, 548, p.121406

Jones, Joshua S., Tullis, Jason A., Haavik, Laurel J., Guldin, James M., Stephen, Fred M. (2014). Monitoring oak-hickory forest change during an unprecedented red oak borer outbreak in the Ozark Mountains: 1990 to 2006. Journal of Applied Remote Sensing. 8,1: 083687.

Jordan, C. F. (1969). Derivation of leaf area index from quality of light on the forest floor. Ecology 50:663-666.

Kalbi, S., Fallah, A. & Shataee, S. (2014). Estimation of forest attributes in the Hyrcanian forests, comparison of advanced space-borne thermal emission and reflection radiometer and satellite pour I’observation de la terre-high resolution grounding data by multiple linear, and classification and regression tree regression models. Journal of Applied Remote Sensing, 8(1), p.083632.

Lambert, J., Drenou, C., Denux, J.P., Balent, G. & Cheret, V. (2013). Monitoring forest decline through remote sensing time series analysis. GIScience & remote sensing, 50(4), pp.437-457.

Lloret, F., Lobo, A., Estevan, H., Maisongrande, P., Vayreda, J. & Terradas, J. (2007). Woody plant richness and NDVI response to drought events in Catalonian (northeastern Spain) forests. Ecology, 88(9), pp.2270-2279.

Matsushita, B., Yang, W., Chen, J., Onda, Y. & Qiu, G. (2007). Sensitivity of the enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) to topographic effects: a case study in high-density cypress forest. Sensors, 7(11), pp.2636-2651.

Nedkov, R. (2017). Orthogonal transformation of segmented images from the satellite Sentinel-2. Comptes rendus de l’Academie bulgare des Sciences, 70(5), pp.687-692.

Qi, J., Chehbouni, A., Huerte, A.R., Kerr, Y.H. & Sorooshian, S. (1994). A modified soil adjusted vegetation index: Remote Sensing Environment, 48(2): pp.119-26.

Recanatesi, F., Giuliani, C. & Ripa, M. (2018). Monitoring Mediterranean Oak decline in a peri-urban protected area using the NDVI and Sentinel-2 images: The case study of Castelporziano State Natural Reserve. Sustainability, 10(9), p.3308.

Rita, A., Camarero, J.J., Nolè, A., Borghetti, M., Brunetti, M., Pergola, N., Serio, C., Vicente‐Serrano, S.M., Tramutoli, V. & Ripullone, F. (2020). The impact of drought spells on forests depends on site conditions: The case of the 2017 summer heat wave in southern Europe. Global change biology, 26(2), pp.851-863.

Rouse J.W., Hass. R.H., Schell, J. A. Deering D,W. (1973). Monitoring Vegetation systems in the Great Plains with ERTS, In Third Earth Resources Technology Satellite -1 Symposium, Washington DC: NASA, pp. 309-317

Traganos, D. & Reinartz, P. (2018). Mapping Mediterranean seagrasses with Sentinel-2 imagery. Marine Pollution Bulletin, 134, pp.197-209.

Vicente-Serrano, S.M., Martin-Hernandez, N., Camarero, J.J., Gazol, A., Sanchez-Salguero, R., Pena-Gallardo, M., El Kenawy, A., Dominguez-Castro, F., Tomas-Burguera, M., Gutierrez, E. & de Luis, M. (2020). Linking tree-ring growth and satellite-derived gross primary growth in multiple forest biomes. Temporal-scale matters. Ecological Indicators, 108, p.105753.

Vicente-Serrano, S.M., Azorin-Molina, C., Peña-Gallardo, M., Tomas-Burguera, M., Domínguez-Castro, F., Martín-Hernández, N., Beguería, S., El Kenawy, A., Noguera, I. & García, M. (2019). A high-resolution spatial assessment of the impacts of drought variability on vegetation activity in Spain from 1981 to 2015. Natural Hazards and Earth System Sciences, 19(6), pp.1189-1213.

Wang, C., He, H. S., & Kabrick, J. M. (2008). A remote sensing-assisted risk rating study to predict oak decline and recovery in the Missouri Ozark Highlands, USA. GIScience & Remote Sensing, 45(4): 406-425.

Wang, J., Sammis, T.W., Gutschick, V.P., Gebremichael, M., Dennis, S.O. & Harrison, R.E. (2010). Review of satellite remote sensing use in forest health studies. The Open Geography Journal, 3(1).