مدلسازی خطر وقوع آتشسوزی در منطقه حفاظتشده دینارکوه، جنوب استان ایلام | ||
| خشک بوم | ||
| دوره 14، شماره 2، مهر 1403، صفحه 197-210 اصل مقاله (1.11 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.29252/aridbiom.2025.22751.2039 | ||
| نویسندگان | ||
| جواد میرزائی1؛ رضا امیدی پور* 2؛ ناهید جعفریان3 | ||
| 11- گروه علوم جنگل، دانشکده کشاورزی، دانشگاه ایلام، ایلام، ایران | ||
| 2گروه مرتع و آبخیزداری، دانشکده کشاورزی، دانشگاه ایلام، ایلام، ایران | ||
| 33- محقق بخش تحقیقات جنگلها، مراتع و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان ایلام، سازمان تحقیقات، آموزش و ترویج | ||
| چکیده | ||
| آتشسوزی تهدیدی جدی برای اکوسیستمهای جنگلی جهان بهویژه در مناطق خشک و نیمهخشک است. درک عوامل کلیدی مؤثر بر وقوع آتشسوزی برای مدیریت مؤثر و کاهش آن ضروری است. به همین دلیل، این مطالعه با هدف مدلسازی خطر وقوع آتشسوزی در جنگلهای نیمهخشک جنوب استان ایلام انجامگرفت. ابتدا نقاط آتشسوزیهای قبلی منطقه با استفاده از تصاویر ماهوارهای MODIS بین سالهای 1380 تا 1402 استخراج شد. عوامل مؤثر بر وقوع آتشسوزی در منطقه در قالب چهار گروه اصلی شامل عوامل توپوگرافی، اقلیمی، پوششگیاهی و انسانی شناسایی شد. برای پیشبینی و مدلسازی پتانسیل وقوع آتش از مدلهای جنگل تصادفی و ماشینبردارپشتیبان استفاده شد. برای ارزیابی دقت دو مدل از شاخص سطح زیر منحنی (AUC) در نمودار ROC استفاده شد. براساس نتایج، میزان رطوبتنسبی هوا، پوششگیاهی، فاصله از جاده و میانگین دمای هوا تأثیرگذارترین و فاصله از جنگل، درصد شیب و جهت جغرافیایی کماهمیتترین عوامل در بروز آتشسوزی منطقه موردمطالعه میباشند. ارزیابی دقت دو مدل موردبررسی نشانداد که مدل جنگل تصادفی (AUC=0.87) دارای دقت بالاتری نسبت به مدل ماشینبردارپشتیبان (AUC=0.82) بود. براساس نتایج مدل جنگل تصادفی، بیش از 59 درصد از سطح منطقه دارای خطر وقوع آتش خیلی کم بودند درحالی که کلاس خطر زیاد و خیلیزیاد بهترتیب 80/1 و 86/0 درصد (بهترتیب 750 و 356 هکتار) از مساحت کل منطقه را دربرگرفتند. باتوجه به تمرکز وقوع آتشسوزیها در مناطق نزدیک به تنها جادهی عبوری از منطقه، پیشنهاد میگردد جهت کاهش و کنترل سریع آتشسوزیهای آتی، اقدامات مدیریتی و تاسیسات اطفا حریق در این منطقه بیش از سایر مناطق باشد. | ||
| کلیدواژهها | ||
| پوشش گیاهی؛ سنجنده مودیس؛ عوامل اقلیمی؛ مدل جنگل تصادفی | ||
| عنوان مقاله [English] | ||
| Modeling the fire risk occurrence in Dinarkoh Protected Area, southern Ilam Province | ||
| نویسندگان [English] | ||
| Javad Mirzaei1؛ Reza omidipour2؛ Nahid Jafarian3 | ||
| 11. Department of Forestry, Faculty of Agriculture, University of Ilam, Ilam, Iran. | ||
| 2Department of Range and Watershed Management, Faculty of Agriculture, Ilam University, Ilam, Iran | ||
| 33. Research Division of Forests, Rangelands and Watershed, Ilam Agricultural and Natural Resources Research Center (AREEO), Ilam, Iran. | ||
| چکیده [English] | ||
| Fires are a serious threat to the world's forest ecosystems, especially in arid and semi-arid regions. Understanding the key factors affecting forest fire dynamics is essential for effective management and mitigation. For this reason, this study aimed to model the risk of forest fires in the semi-arid forests of southern Ilam province. First, the locations of previous fires in the region were extracted using MODIS satellite images between 2000 and 2023. The factors affecting on the fire’s occurrence were identified and categorized in four main groups including topography, climate, vegetation and human factors. Random forest (RF) and support vector machine (SVM) models were used to predict and model the potential for fire occurrence. The area under the curve (AUC) in the ROC curve was used to evaluate the accuracy of the two models. Based on the results, the relative humidity, vegetation, distance from the road and average air temperature were the most influential and the distance from the forest, slope percentage and geographical direction were the least important factors in fires occurrence in the studied region. The accuracy assessment of the two models showed that the RF model (AUC=0.87) had a higher accuracy than SVM model (AUC=0.82). Based on the results of the RF model, more than 59 percent of the area had a very low risk of fire occurrence, while the high and very high-risk classes covered 1.80 and 0.86 percent (750 and 356 hectares, respectively) of the total area of the region. Given the concentration of fires in areas close to road, it is recommended that management measures and firefighting facilities be more in place in this area than in other areas to reduce and quickly control future fires. | ||
| کلیدواژهها [English] | ||
| Vegetation, MODIS sensor, Climatic factors, Random Forest model | ||
| مراجع | ||
|
[1]. Adab H., Kanniah K., & Solaimani K. (2011). GIS-based probability assessment of fire risk in grassland and forested landscapes of Golestan province, Iran. Environmental Science, Geography, 19, 170-175.
[2]. Adab, H., Kanniah, K.D., & Solaimani, K. (2013). Modeling forest fire risk in the northeast of Iran using remote sensing and GIS techniques. Natural Hazards, 65(2), 1723-1743. doi: 10.1007/s11069-012-0450-8.
[3]. Artes, T., Cencerrado, A., Cortes, A., & Margalef, T. (2013). Relieving the effects of uncertainty in forest fire spread prediction by hybrid MPI-OpenMP parallel strategies. International Conference on Computational science, Procedia Computer Science, 18, 2278-2287. https://doi.org/10.1016/j.procs.2013.05.399.
[4]. Babu, K.N., Gour, R., Ayushi, K., Ayyappan, N., & Parthasarathy, N. (2023). Environmental drivers and spatial prediction of forest fires in the Western Ghats biodiversity hotspot, India: An ensemble machine learning approach. Forest Ecology and Management, 504, 121057. doi: 10.1016/j.foreco.2023.121057.
[5]. Bagherabadi, R., Shikhkanloo Milan, F., & Zarei Mohammadabad, M. (2022). Evaluation of fire risk in the Zagros forests (Case study: Dalahu County). Management of Natural Ecosystems, 2(2), 60-72. Doi: 10.22034/emj.2022.254859 [in Farsi].
[6]. Bahrami-Pichaghchi, H., Norooz-Valashedi, R., & Gholami Sefidkouhi, M. A. (2024). Investigating the trend of wildfires and its relationship with climate variables using satellite data (case study: Mazandaran province). Journal of Natural Environmental Hazards, 13(39), 127-140. Doi:10.22111/jneh.2023.45573.1967 [in Farsi].
[7]. Bazyar, M., Oladi Ghadikolaii, J., Pourghasemi, H.R., & Serajyan maralan M.R. (2018). Zoning and Investigation of Factors Affecting Forest Fire Using Evidential Belief Function Algorithm and Support Vector Machine in Boyer Ahmad City. Iranian Journal of Forests and Rangelands Protection Research, 17(2), 197 -222. doi: 10.22092/ijfrpr.2020.128649.1406 [in Farsi]
[8]. Benbakkar, H.A., Souidi, Z., Bardadi, A., & Bento-Gonçalves, A. (2024). Forest Fires Risk in A semi -Arid Region: A Case Study in Western Alger. International Journal of Professional, Business. Review, 9(5), 1-20.
[9]. Chamandeh, J., Alvaninejad, S., & Gholami, P. (2017). A survey of composition and diversity of herbaceous species after a fire in Persian Oak forests of Southern Zagros. Journal of Wood & Forest Science and Technolog, 24(3), 1-15. doi: 10.22069/jwfst.2017.11742.1620 [in Farsi]
[10]. Charizanos, G., & Demirhan, H. (2023). Bayesian prediction of wildfire event probability using normalized difference vegetation index data from an Australian forest. Ecological Informatics, 73, 101899. doi: 10.1016/j.ecoinf.2022.101899.
[11]. Ellison, D., Morris, C.E., Locatelli, B., Sheil, D., Cohen, J., Murdiyarso, D., Gutierrez, V., Van Noordwijk, M., Creed, I.F., Pokorny, J., & Gaveau, D. (2017). Trees, forests and water: Cool insights for a hot world. Global Environmental Change, 43, 51-61. doi: 10.1016/j.gloenvcha.2017.01.002.
[12]. Emami, H., & Shahriari, H. (2020). Quantification of environmental and human factors in the occurrence of forest fire with RS and GIS methods. Arsbaran protected areas. Research Quarterly Geographical Data (SEPEHR), 28(112), 35- 53. doi: 10.22131/sepehr.2020.38606 [in Farsi].
[13]. Enoh, M.A., Okeke, U.C., & Narinua, N. Y. (2021). Identification and modelling of forest fire severity and risk zones in the Cross – Niger transition forest with remotely sensed satellite data. The Egyptian Journal of Remote Sensing and Space Science, 24(3), 879-887. doi: 10.1016/j.ejrs.2021.09.002.
[14]. Eskandari, S., Pourghasemi, H.R., |& Tiefenbacher, J.P. (2020). Relations of land cover, topography, and climate to fire occurrence in natural regions of Iran: Applying new data mining techniques for modeling and mapping fire danger. Forest Ecology and Management, 473, 118338. doi: 10.1016/j.foreco.2020.118338.
[15]. Farfán, M., Dominguez, C., Espinoza, A., Jaramillo, A., Alcántara, C., Maldonado, V., Tovar, I., & Flamenco, A. (2021). Forest fire probability under ENSO conditions in a semi-arid region: a case study in Guanajuato. Environmental Monitoring and Assessment, 193 (10), 684. doi: 10.1007/s10661-021-09494-0.
[16]. Gerdzheva, A.A. (2014). A comparative analysis of different wildfire risk assessment models (a case study for Smolyan district, Bulgaria. European Journal of Geography, 5 (3), 22 -36.
[17]. Huang, L., Zhou, M., Lv, J., & Chen, K. (2020). Trends in global research in forest carbon sequestration: A bibliometric analysis. Journal of Cleaner Production, 252, 119908. doi: doi.org/10.1016/j.jclepro.2019.119908.
[18]. Jafari, M., Karamshahi, A., Heydari, M., Mirzaei, J., & Jafarian, N. (2024). Evaluation of oak decline in relation to the diversity of woody species, soil properties and physiographic factors in southern Zagros forests. Journal of Arid Biome, 14(1), 91-106. doi: 10.29252/aridbiom.2024.21417.2006.
[19]. Jahdi, R.; Beiranvandi, V., & Amini, H. (2024). Wildfire Risk Assessment in Zagros Forests using Geographic Information System and Best-Worst Method (BWM) (Case Study: Dore Chegeni County, Lorestan Province). Journal of Geography and Environmental Studies, 13 (49): 68-85. https://www.magiran.com/p2740687 [in Farsi].
[20]. Javanmiri Pour., M., Valipour, J., & Hasanzadeh, A. (2022). Study of structural factors and effective motives in causing forest and pasture fires in semi-arid ecosystems of the Zagros Mountain. Journal of Arid Biome, 11(2), 15-27. doi: 10.29252/aridbiom.2022.18321.1888.
[21]. Kermani, F., Rayegani., B., Nezami, B., Goshtasb, H., & Khosravi, H. (2016). Assessing the vegetation trends in arid and semi-arid regions (Case study: Touran Protected Area). Desert Ecosystem Engineering Journal, 6(17), 1-14. doi: 10.22052/6.17.1 [in Farsi].
[22]. Kolanek, A., Szymanowski, M., & Raczyk, A. (2021). Human activity affects forest fires: the impact of anthropogenic factors on the density of forest fires in Poland. Forests, 12(6), 728. doi: 10.3390/f12060728.
[23]. Lal, R. (2003). Soil erosion and the global carbon budge. Environment International, 29(4), 437-450. doi: 10.1016/S0160-4120(02)00192-7.
[24]. Merino-de-Miguela, S., Huescab, M., & González-Alonsob, F. (2010). Modis reflectance and active fire data for burn mapping and assessment at regional level. Ecological Modelling, 221(1),67–74. doi: 10.1016/j.ecolmodel.2009.09.015.
[25]. Michael, Y., Helman, D., Glickman, O., Gabay, D., Brenner, S., & Lensky, I.M. (2020). Forecasting fire risk with machine learning and dynamic information derived from satellite vegetation index time-series. Science of the Total Environment, 746, 142844. doi: 10.1016/j.scitotenv.2020.142844.
[26]. Moghim, S., & Mehrabi, M. (2024). Wildfire assessment using machine learning algorithms in different region. Fire Ecology, 20, 104. doi: 10.1186/s42408-024-00335-2.
[27]. Mohammadi, F., Bavaghar, M.P., & Shabanian, N. (2014). Forest fire risk zone modeling using logistic regression and GIS: an Iranian case study. Small-scale Forestry, 13, 117-125. doi: 10.1007/s11842-013-9244-4.
[28]. Morovati, M., & Karami, P. (2024). Modeling the seasonal wildfire cycle and its possible effects on the distribution of focal species in Kermanshah Province, western Iran. PLoS ONE, 19(10), e0312552. doi: 10.1371/journal.pone.0312552.
[29]. Najafi, A., Irannezhad, M. H., Sotoudeh, A., Mokhtari, M.H., & Kiani, B. (2016). Modeling and Risk Mapping of Forest Fires using Remote Sensing and GIS (Case Study: Baghe-Shadi Protected Area, Yazd Province). Iranian Journal of Applied Ecology, 4 (14), 13-26. doi: 10.18869/acadpub.ijae.4.14.13.
[30]. Pan, Y., Birdsey, R.A., Fang, J., Houghton, R., Kauppi, P.E., Kurz, W.A., Phillips, O.L., Shvidenko, A., Lewis, S.L., Canadell, J.G., & Ciais, P. (2011). A large and persistent carbon sink in the world’s forests. Science, 333 (6045), 988–993. doi: 10.1126/science.1201609.
[31]. Rodriguez-Jimenez, F., Lorenzo, H., Acuna-Alonso, C., & Alvarez, X. (2023). PLS-PM analysis of forest fires using remote sensing tools. The case of Xurés in the Transboundary Biosphere Reserve. Ecological Informatics, 75, 102010. doi: 10.1016/j.ecoinf.2023.102010.
[32]. Saha, S., Bera, B., Shit, P.K., Bhattacharjee, S., & Sengupta, N. (2023). Prediction of forest fire susceptibility applying machine and deep learning algorithms for conservation priorities of forest resources. Remote Sensing Applications: Society and Environment, 29, 100917. doi: 10.1016/j.rsase.2022.100917.
[33]. Saranya, K.R.L., Sudhakar Reddy, C., Prasada Rao, P.V.V., & Jha, C.S. (2014). Decadal time -scale monitoring of forest fires in Similipal Biosphere Reserve, India using remote sensing and GIS. Environmental Monitoring and Assessment, 186, 3283 –3296. doi: 10.1007/s12040-016-0685-y.
[34]. Scott, J. H., Thompson, M. P., & Calkin, D. E. (2013). A Wildfire Risk Assessment Framework for Land and Resource Management. USDA Forest Service. Rocky Mountain Research Station. doi: 10.2737/rmrs-gtr-315.
[35]. Serpa, D., Ferreira, R.V., Machado, A.I., Cerqueira, M.A., & Keizer. J.J. (2020). Mid-term post-fire losses of nitrogen and phosphorus by overland flow in two contrasting eucalypt stands in north-central Portugal. Science of The Total Environment, 705, 135843. doi: 10.1016/j.scitotenv.2019.135843.
[36]. Soualah, L., Bouzekri, A., & Chenchouni, H. (2024). Hoping the best, expecting the worst: Forecasting Forest fire risk in Algeria using fuzzy logic and GIS. Trees, Forests and People, 17, 100614. doi: 10.1016/j.tfp.2024.100614.
[37]. Sowmya, S.V., & Somashekar, R.K. (2010). Application of remote sensing and geographical information system in mapping forest fire risk zone at Bhadra wildlife sanctuary, India. Journal of Environmental Biology, 31(6), 969-974.
[38]. Szpakowski, D.M., & Jensen, J.L.R. (2019). A Review of the Applications of Remote Sensing in Fire Ecology. Remote Sensing, 11, 2638. doi: 10.3390/rs11222638.
[39]. Veysi, R., Fattahi, B., & Khosrow Beigi, S. (2022). Predicting and preparing a risk map of rangeland fires using random forest algorithms and support vector machine (Case study: Arak rangelands). Journal of Rangeland, 16(1), 413-426. doi:20.1001.1.20080891.1401.16.2.13.7 [in Farsi].
[40]. Watson, J.E., Evans, T., Venter, O., Williams, B., Tulloch, A., Stewart, C., Thompson, I., Ray, J.C., Murray, K., Salazar, A., & McAlpine, C. (2018). The exceptional value of intact forest ecosystems. Nature Ecology & Evolution, 2(4), 599-610. doi: 10.1038/s41559-018-0490-x.
[41]. Xie, Y., & Peng, M. (2019). Forest fire forecasting using ensemble learning approaches. Neural Computing and Applications, 31, 4541–4550. doi: 10.1007/s00521-018-3515-0.
[42]. Xu, H., & Schoenberg, F.P. (2011). Point process modeling of wildfire hazard in Los Angeles County, California. Annals of Applied Statistics, 5(2), 684-704. doi: 10.1214/10-AOAS401
[43]. Yin, S., Wang, X., Guo, M., Santoso, H., & Guan, H. (2020). The abnormal change of air quality and air pollutants induced by the forest fire in Sumatra and Borneo in 2015. Atmospheric Research, 243, 105027. doi: 10.1016/j.atmosres.2020.105027.
[44]. Zhao L., Ge, Y., Guo, S., Li, X., & Chen, S. (2024). Forest fire susceptibility mapping based on precipitation-constrained cumulative dryness status information in Southeast China: A novel machine learning modeling approach. Forest Ecology and Management, 558, 121771. doi: 10.1016/j.foreco.2024.121771..
| ||
|
آمار تعداد مشاهده مقاله: 284 تعداد دریافت فایل اصل مقاله: 86 |
||