نشریه علمی - پژوهشی مرتع و آبخیزداری

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه تهران، کرج، ایران

10.22059/jrwm.2024.380584.1780

چکیده

شناخت و نقشه‌سازی حساسیت جنگل‌ها به آتش‌سوزی برای حفظ اکوسیستم‌ها و تنوع زیستی دارای اهمیت است. این مطالعه با بررسی قابلیت سری‌زمانی تصاویر ماهواره‌ی لندست ۸ و تولید مدلی کارا در بستر سامانه گوگل ارث انجین (GEE) توانست حساسیت جنگل‌های استان کردستان به آتش‌سوزی را در فاصله زمانی ده سال اخیر از سال ۲۰۱۳ الی ۲۰۲۳ و در دو محدوده‌ی مطالعاتی واقع در شهرستان‌های مریوان، سروآباد و بانه پهنه‌بندی کند و اطلاعات ارزشمندی برای مدیریت پیشگیرانه زمین و تخصیص مؤثر منابع به منظور پیشگیری و کاهش تأثیرات آتش‌سوزی جنگل‌ها در منطقه کردستان ارائه ‌دهد. در این مطالعه برای شناسایی حریق جنگلی از شاخص نسبت سوختگی نرمال شده (NBR) برای تصاویر قبل و بعد از فصل آتش‌سوزی استفاده شد. به منظور بهبود نتایج طبقه‌بندی شاخص‌های گیاهی، مسکونی و پهنه‌های آبی به عنوان منطقه بدون حریق بارزسازی شدند. برای دست‌یابی به بهترین صحت طبقه‌بندی از مدل جنگل تصادفی (RF) در سامانه GEE استفاده گردیده است. سپس باتهیه نمونه‌های تعلیمی مناسب از نتایج بارزسازی، طبقه‌بندی تصاویر با مدل RF به تعداد ۵۰ درخت تصمیم‌گیری در سامانه GEE انجام شد. به منظور اطمینان از صحت نمونه‌های تعلیمی انتخاب شده، نتایج نقشه‌سازی آتش‌سوزی با داده‌های نقطه‌ای حریق اداره‌ی منابع طبیعی استان کردستان مقایسه شد. نتایج طبقه‌بندی در دو محدوده‌ی مطالعاتی جنگلی، منطقه مریوان و سروآباد در سال‌های ۲۰۱۶، ۲۰۱۸ و ۲۰۲۰ و منطقه بانه در سال ۲۰۱۸ صحت کلی ۹۹ درصد و ضریب کاپای ۹۷/۰ را نشان داد. نتایج حاصل شده در این تحقیق علاوه بر تاکید بر قابلیت تصاویر لندست‌۸ در نقشه‌سازی حساسیت جنگل، نشان دهنده‌ی صحت قابل قبول مدلRF در این زمینه است.

کلیدواژه‌ها

عنوان مقاله [English]

Zoning Forest Fires Using the Random Forest Model in the Forests of Kurdistan Province in the Google Earth Engine Platform

نویسندگان [English]

  • Abdulmajed Bostani
  • Sharareh Pourebrahim
  • Afshin Danehkar

Department of Environment, Faculty of Natural resources, University of Tehran, Karaj, Iran

چکیده [English]

Recognizing and mapping the sensitivity of forests to fires is crucial for the preservation of ecosystems and biodiversity. This study, utilizing the time-series capability of Landsat 8 satellite imagery and developing an efficient model within the Google Earth Engine (GEE) platform, managed to map the sensitivity of Kurdistan province forests to fires over the the past decade, from 2013 to 2023, in two study areas located in the Marivan, Sarvabad, and Baneh counties. It provided valuable information for land use management and effective resource allocation to prevent and mitigate the impacts of forest fires in the Kurdistan region. The Normalized Burn Ratio (NBR) index was applied to pre- and post-fire season images to detect forest fires. To enhance classification results, areas such as vegetation, residential zones, and water bodies were highlighted as non-fire regions. The Random Forest (RF) model within the GEE platform was employed to achieve the highest classification accuracy. Appropriate training samples were derived from the highlighted results, and image classification using the RF model with 50 decision trees was performed on the GEE platform.To ensure the reliability of the selected training samples, the fire mapping results were compared with point-based fire data from the Kurdistan Province Natural Resources Department. The classification results for the two forest study areas- Marivan and Sarvabad regions in 2016, 2018, and 2020, and the Baneh region in 2018-demonstrated an overall accuracy of 99% and a Kappa coefficient of 0.97. The findings of this study underscore the capability of Landsat 8 imagery in mapping forest fire susceptibility and confirm the acceptable accuracy of the RF model in this context.

کلیدواژه‌ها [English]

  • Wildfire
  • Enhancement
  • Google Earth Engine Platform
  • dNBR Index
  • Random Forest Model
Alcaras, E., Costantino, D., Guastaferro, F., Parente, C., & Pepe, M. (2022). Normalized Burn Ratio Plus (NBR+): A New Index for Sentinel-2 Imagery. Remote Sensing, 14(7). https://doi.org/10.3390/rs14071727
Amos, C., Petropoulos, G. P., & Ferentinos, K. P. (2018). Determining the use of Sentinel-2A MSI for wildfire burning & severity detection. International Journal of Remote Sensing, 40(3), 905-930. https://doi.org/10.1080/01431161.2018.1519284
Badda, H., Cherif, E. K., Boulaassal, H., Wahbi, M., Yazidi Alaoui, O., Maatouk, M., Bernardino, A., Coren, F., & El Kharki, O. (2023). Improving the Accuracy of Random Forest Classifier for Identifying Burned Areas in the Tangier-Tetouan-Al Hoceima Region Using Google Earth Engine. Remote Sensing, 15(17). https://doi.org/10.3390/rs15174226
Bartalev, S. A., & Stytsenko, F. V. (2021). Assessment of Forest-Stand Destruction by Fires Based on Remote-Sensing Data on the Seasonal Distribution of Burned Areas. Contemporary Problems of Ecology, 14(7), 711-716. https://doi.org/10.1134/S1995425521070027
Bhomi, A. K., Poudyal, R., Tolange, S. K., & Chaudhary, S. (2024). Assessing the Impact of Urban Expansion on Forest Cover using LULC Maps, NDVI, and NDBI: A Case Study of Kathmandu District. Journal on Geoinformatics, Nepal, 1-7.
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
Cai, L., & Wang, M. (2020). Is the RdNBR a better estimator of wildfire burn severity than the dNBR? A discussion and case study in southeast China. Geocarto International, 37(3), 758-772. https://doi.org/10.1080/10106049.2020.1737973
Cardille, J. A., Crowley, M. A., Saah, D., & Clinton, N. E. (2023). Cloud-Based Remote Sensing with Google Earth Engine. 115-148.
Charizanos, G., & Demirhan, H. (2023). Bayesian prediction of wildfire event probability using normalized difference vegetation index data from an Australian forest. Ecological Informatics, 73. https://doi.org/10.1016/j.ecoinf.2022.101899
Chen, D., Fu, C., Hall, J. V., Hoy, E. E., & Loboda, T. V. (2021). Spatio-temporal patterns of optimal Landsat data for burn severity index calculations: Implications for high northern latitudes wildfire research. Remote Sensing of Environment, 258. https://doi.org/10.1016/j.rse.2021.112393
Collins, L., Griffioen, P., Newell, G., & Mellor, A. (2018). The utility of Random Forests for wildfire severity mapping. Remote Sensing of Environment, 216, 374-384. https://doi.org/10.1016/j.rse.2018.07.005
Collins, L., McCarthy, G., Mellor, A., Newell, G., & Smith, L. (2020). Training data requirements for fire severity mapping using Landsat imagery and random forest. Remote Sensing of Environment, 245. https://doi.org/10.1016/j.rse.2020.111839
Danneyrolles, V., Smetanka, C., Fournier, R., Boucher, J., Guindon, L., Waldron, K., Bourdon, J.-F., Bonfils, D., Beaudoin, M., Ibarzabal, J., Rossi, S., & Boucher, Y. (2024). Assessing spatial patterns of burn severity for guiding post-fire salvage logging in boreal forests of Eastern Canada. Forest Ecology and Management, 556. https://doi.org/10.1016/j.foreco.2024.121756
Davis, K. T., Peeler, J. L., Fargione, J. E., Haugo, R. D., Metlen, K. L., Robles, M. D., & Woolley, T. (2024). Tamm review: A meta-analysis of thinning, prescribed fire, and wildfire effects on subsequent wildfire severity in conifer dominated forests of the Western US. Forest Ecology and Management.
Dindaroglu, T., Babur, E., Yakupoglu, T., Rodrigo-Comino, J., & Cerdà, A. (2021a). Evaluation of geomorphometric characteristics and soil properties after a wildfire using Sentinel-2 MSI imagery for future fire-safe forest. Fire Safety Journal, 122, 103318. https://doi.org/https://doi.org/10.1016/j.firesaf.2021.103318
Dindaroglu, T., Babur, E., Yakupoglu, T., Rodrigo-Comino, J., & Cerdà, A. (2021b). Evaluation of geomorphometric characteristics and soil properties after a wildfire using Sentinel-2 MSI imagery for future fire-safe forest. Fire Safety Journal, 122. https://doi.org/10.1016/j.firesaf.2021.103318
Epoka U, & M, U. o. (2020). Testing NDVI,tree cover density and land cover type as fuel indicators in the wildfire spread capacity index(WSCI): case of Montenegro. 48. https://doi.org/10.15835/48411993
Eskandari, S., & Chuvieco, E. (2015). Fire danger assessment in Iran based on geospatial information. International Journal of Applied Earth Observation and Geoinformation, 42, 57-64. https://doi.org/10.1016/j.jag.2015.05.006
Feliu, S., Pedro, D., Andrew, T., & M, F. (2021). Estimating hetrogeneous wildfire effect using synthetic control and satellite remote sensing. Remote Sensing of Environment, 265.
Fernandez-Carrillo, A., McCaw, L., & Tanase, M. A. (2019). Estimating prescribed fire impacts and post-fire tree survival in eucalyptus forests of Western Australia with L-band SAR data. Remote Sensing of Environment, 224, 133-144. https://doi.org/https://doi.org/10.1016/j.rse.2019.02.005
Gibson, R., Danaher, T., Hehir, W., & Collins, L. (2020). A remote sensing approach to mapping fire severity in south-eastern Australia using sentinel 2 and random forest. Remote Sensing of Environment, 240, 111702. https://doi.org/10.1016/j.rse.2020.111702
Giddey, B. L., Baard, J. A., & Kraaij, T. (2022). Verification of the differenced Normalised Burn Ratio (dNBR) as an index of fire severity in Afrotemperate Forest. South African Journal of Botany, 146, 348-353. https://doi.org/10.1016/j.sajb.2021.11.005
Hamed, A., Kanniah, D., & S, K. (2011). GIS-based Probability Assessment of Fire Risck in Grassland and Forest Landscapes of Golestan Province, Iran. international conference Environmental and Computer science, 19.
Heydari, S. S., & Mountrakis, G. (2018). Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites. Remote Sensing of Environment, 204, 648-658. https://doi.org/10.1016/j.rse.2017.09.035
Jaafari, A., Gholami, D. M., & Zenner, E. K. (2017). A Bayesian modeling of wildfire probability in the Zagros Mountains, Iran. Ecological Informatics, 39, 32-44. https://doi.org/10.1016/j.ecoinf.2017.03.003
Konkathi, P., & Shetty, A. (2021). Inter comparison of post-fire burn severity indices of Landsat-8 and Sentinel-2 imagery using Google Earth Engine. Earth Science Informatics, 14(2), 645-653. https://doi.org/10.1007/s12145-020-00566-2
Krawchuk, M. A., Moritz, M. A., Parisien, M.-A., Van Dorn, J., & Hayhoe, K. (2009). Global Pyrogeography: the Current and Future Distribution of Wildfire. PLOS ONE, 4(4), e5102. https://doi.org/10.1371/journal.pone.0005102
Le, H. V., Hoang, D. A., Tran, C. T., Nguyen, P. Q., Tran, V. H. T., Hoang, N. D., Amiri, M., Ngo, T. P. T., Nhu, H. V., Hoang, T. V., & Tien Bui, D. (2021). A new approach of deep neural computing for spatial prediction of wildfire danger at tropical climate areas. Ecological Informatics, 63. https://doi.org/10.1016/j.ecoinf.2021.101300
Lee, K., van Leeuwen, W. J. D., Gillan, J. K., & Falk, D. A. (2024). Examining the Impacts of Pre-Fire Forest Conditions on Burn Severity Using Multiple Remote Sensing Platforms. Remote Sensing, 16(10). https://doi.org/10.3390/rs16101803
Liu, W., Guan, H., Hesp, P. A., & Batelaan, O. (2023). Remote sensing delineation of wildfire spatial extents and post-fire recovery along a semi-arid climate gradient. Ecological Informatics, 78, 102304. https://doi.org/https://doi.org/10.1016/j.ecoinf.2023.102304
Massetti, A., Rüdiger, C., Yebra, M., & Hilton, J. (2019). The Vegetation Structure Perpendicular Index (VSPI): A forest condition index for wildfire predictions. Remote Sensing of Environment, 224, 167-181. https://doi.org/10.1016/j.rse.2019.02.004
Moghadam M. H, R., A, F., Z, M., & S, P. (2024). Burned area assessment using Sentinel-2A satellite imagery and DNBR spectral index (Case study: forest areas on the anticline in the Khaiz region, Iran). BOHR International Journal of Civil Engineering and Environmental Science, 2(1), 12-20. https://doi.org/10.54646/bijcees.2024.15
Mueller, S. E., Thode, A. E., Margolis, E. Q., Yocom, L. L., Young, J. D., & Iniguez, J. M. (2020). Climate relationships with increasing wildfire in the southwestern US from 1984 to 2015. Forest Ecology and Management, 460. https://doi.org/10.1016/j.foreco.2019.117861
Mutanga, O., & Kumar, L. (2019). Google Earth Engine Applications. Remote Sensing, 11(5). https://doi.org/10.3390/rs11050591
Ngadze, F., Mpakairi, K. S., Kavhu, B., Ndaimani, H., & Maremba, M. S. (2020). Exploring the utility of Sentinel-2 MSI and Landsat 8 OLI in burned area mapping for a heterogenous savannah landscape. PLOS ONE, 15(5), e0232962. https://doi.org/10.1371/journal.pone.0232962
Parks, S., Holsinger, L., Koontz, M., Collins, L., Whitman, E., Parisien, M.-A., Loehman, R., Barnes, J., Bourdon, J.-F., Boucher, J., Boucher, Y., Caprio, A., Collingwood, A., Hall, R., Park, J., Saperstein, L., Smetanka, C., Smith, R., & Soverel, N. (2019). Giving Ecological Meaning to Satellite-Derived Fire Severity Metrics across North American Forests. Remote Sensing, 11(14). https://doi.org/10.3390/rs11141735
Pausas, J. G., & Keeley, J. E. (2019). Wildfires as an ecosystem service. Frontiers in Ecology and the Environment, 17(5), 289-295. https://doi.org/https://doi.org/10.1002/fee.2044
Ponomarev, E., Zabrodin, A., & Ponomareva, T. (2022). Classification of Fire Damage to Boreal Forests of Siberia in 2021 Based on the dNBR Index. Fire, 5(1). https://doi.org/10.3390/fire5010019
Rodriguez-Jimenez, F., Novo, A., & V. Hall, J. (2024). Influence of wildfires on the conflict (2006–2022) in eastern Ukraine using remote sensing techniques (MODIS and Sentinel-2 images). Remote Sensing Applications: Society and Environment, 35. https://doi.org/10.1016/j.rsase.2024.101240
Sharma, P., Chettri, N., Uddin, K., Wangchuk, K., Joshi, R., Tandin, T., Pandey, A., Gaira, K. S., Basnet, K., Wangdi, S., Dorji, T., Wangchuk, N., Chitale, V. S., Uprety, Y., & Sharma, E. (2020). Mapping human‒wildlife conflict hotspots in a transboundary landscape, Eastern Himalaya. Global Ecology and Conservation, 24. https://doi.org/10.1016/j.gecco.2020.e01284
Sinha, A., Nikhil, S., Ajin, R. S., Danumah, J. H., Saha, S., Costache, R., Rajaneesh, A., Sajinkumar, K. S., Amrutha, K., Johny, A., Marzook, F., Mammen, P. C., Abdelrahman, K., Fnais, M. S., & Abioui, M. (2023). Wildfire Risk Zone Mapping in Contrasting Climatic Conditions: An Approach Employing AHP and F-AHP Models. Fire, 6(2). https://doi.org/10.3390/fire6020044
Sivrikaya, F., Günlü, A., Küçük, Ö., & Ürker, O. (2024a). Forest fire risk mapping with Landsat 8 OLI images: Evaluation of the potential use of vegetation indices. Ecological Informatics, 79, 102461. https://doi.org/https://doi.org/10.1016/j.ecoinf.2024.102461
Sivrikaya, F., Günlü, A., Küçük, Ö., & Ürker, O. (2024b). Forest fire risk mapping with Landsat 8 OLI images: Evaluation of the potential use of vegetation indices. Ecological Informatics, 79. https://doi.org/10.1016/j.ecoinf.2024.102461
Smith, C. W., Panda, S. K., Bhatt, U. S., Meyer, F. J., Badola, A., & Hrobak, J. L. (2021). Assessing Wildfire Burn Severity and Its Relationship with Environmental Factors: A Case Study in Interior Alaska Boreal Forest. Remote Sensing, 13(10). https://doi.org/10.3390/rs13101966
Tariq, A., Shu, H., Gagnon, A. S., Li, Q., Mumtaz, F., Hysa, A., Siddique, M. A., & Munir, I. (2021). Assessing Burned Areas in Wildfires and Prescribed Fires with Spectral Indices and SAR Images in the Margalla Hills of Pakistan. Forests, 12(10). https://doi.org/10.3390/f12101371
Widya, L. K., & Lee, C.-W. (2024). Geospatial technologies for estimating post-wildfire severity through satellite imagery and vegetation types: a case study of the Gangneung Wildfire, South Korea. Geosciences Journal, 28(2), 247-260. https://doi.org/10.1007/s12303-023-0045-2
Williams, T., Williams, B. J., & Song, B. (2014). Modeling a historic forest fire using GIS and FARSITE. Mathematical and Computational Forestry and Natural-Resource Sciences, 6, 80-88.