پیش‌بینی احتمال خشکیدگی جنگل‌های استان لرستان با استفاده از رویکرد مدل‌سازی ترکیبی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد ارزیابی و آمایش سرزمین، دانشکده منابع طبیعی، دانشگاه صنعتی اصفهان، اصفهان، ایران

2 دانشیار گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه صنعتی اصفهان

3 دانشیار، گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه صنعتی اصفهان، اصفهان، ایران

4 استادیار، گروه محیط زیست، دانشکده منابع طبیعی، دانشگاه صنعتی اصفهان، اصفهان، ایران

5 استادیار، گروه مرتع و آبخیزداری، دانشکده منابع طبیعی، دانشگاه صنعتی اصفهان، اصفهان، ایران

چکیده

شناسایی مناطق جنگلی مستعد خشکیدگی به منظور انجام اقدامات پیشگیرانه می‌تواند نقش بسزایی در مبارزه با این پدیده ایفا کند. مطالعات قبلی حاکی از کارآمدی مدل‌سازی در شناسایی این‌گونه مناطق است. از این‏رو برای شناسایی مناطق جنگلی مستعد خشکیدگی در استان لرستان از 15 مدل به صورت ترکیبی استفاده شد. مناطقی از جنگل که دارای زوال بالای 50%  بودند به عنوان متغیر وابسته و عوامل محیطی میانگین بارندگی سالیانه، میانگین دمای سالیانه، میانگین رطوبت نسبی، شاخص خشکی، شاخص خشکسالی، تبخیر و تعرق، شاخص گرد و غبار، فاصله از اراضی کشاورزی و آبراهه‌ها، شیب، جهت و NDVI به عنوان متغیرهای مستقل وارد مدل‌ها شدند. میزان AUC هر مدل در نقشه خروجی حاصل از آن ضرب و میانگین 15 مدل به عنوان مدل ترکیبی در نظر گرفته شد. نقشه احتمال خشکیدگی حاصله بیانگر افزایش احتمال خشکیدگی از قسمت‌های مرکزی جنگل‌های استان به سمت قسمت‌های جنوب و جنوب غربی بود. مدل‌های جنگل تصادفی و ماشین بردار پشتیبان با AUC برابر 1 بالاترین و مدل Bioclim با AUC برابر با 75/0 کمترین کارایی را داشتند. طبق مدل ترکیبی حدود 7/23، 5/7 و 5/19 درصد از جنگل‌های استان لرستان به ترتیب احتمال خشکیدگی کم، متوسط و زیاد را دارا هستند. عوامل اقلیمی شاخص خشکی، بارش، دما و تبخیر و تعرق به ترتیب بیشترین تأثیرگذاری را در مدل‌ها داشتند. پژوهش پیش رو علاوه بر تأکید بر کارایی مدل‌سازی در شناسایی مناطق جنگلی دارای احتمال خشکیدگی، نشان داد که استفاده ترکیبی از مدل‌ها نتایج بهتری را نسبت به استفاده مجزا از آن‌ها به بار می‌آورد.
 
 

کلیدواژه‌ها


عنوان مقاله [English]

Probabilistic prediction of forest decline in Lorestan province using a combined modeling approach

نویسندگان [English]

  • O. Ghadirian 1
  • Mahmood reza Hemami 2
  • A. Soffianian 3
  • S. Pourmanaphi 4
  • M. Malekian 4
  • M. Tarkesh 5
2 Associate Professor of environment science, Department of Natural Resources, Isfahan University of Technology
چکیده [English]

Identifying forest areas susceptible to decline in order to take preventive measures can play a significant role in inhibiting this phenomenon. Previous studies suggest the high performance of modeling to identify such areas. Hence, we used 15 models to identify forest areas prone to decline in Lorestan province. For modeling, forest areas with over 50% tree mortality were used as dependent variable, and environmental factors including annual mean rainfall, annual mean temperature, relative humidity, aridity index, evapotranspiration, dust storm index, drought index, distance to surface waters and agricultural lands, slope, aspect and NDVI as independent variables were introduced into the models. AUC of each model was multiplied by its output and the mean of these models was considered as the combined model. The forest decline risk map resulted from the combined model indicated a decline trend from central parts of the Lorestan’s forests to the south and south-western parts. The Random forest and Support vector machine were recognized as the best models with AUC value of 1 and the Bioclim as the weakest model with AUC of 0.75. According to the combined model, approximately 23.7%, 7.5%, and 19.5% of the studied forests had low, medium, and high risk of decline respectively. The climatic factors including aridity index, rainfall, temperature, and evapotranspiration were the most influencing environmental factors, respectively. The present research, in addition to emphasizing the modeling efficiency in identification of forest areas susceptible to decline, indicated that the combination of models yields better result rather than their separate use.

کلیدواژه‌ها [English]

  • Zagros forests decline
  • Climate change
  • adaptive measures
  • random forest
  • Support Vector Machine
-    Abasi, S., Hoseini, S., Pileh Var, B. and Zare, H. 2009. The effect of Protection on Biodiversity of wooden species in Oshtrankouh Lorestan. Forest Journal of Iran, 1: 1-10 (In Persian).
-    Achard, F., Eva, D.H., Stibing, H., Mayaux, P., Gallego, J., Richards, T. and Malingreau, J. 2002. Determination of deforestation rates of world’s humid tropical forests. Science, 297: 999-1006.
-    Ahmadi, Sh., Zahedi Amiri, Gh. and Marvie Mohadjer, M.R. 2016. Mapping Brant’s oak (Quercus brantii Lindl.) mortality using geostatistical methods in Dasht-e Barm, Fars Province. Iranian Journal of Forest and Poplar Research, 24(3): 439-450 (In Persian).
-    Alizadeh, A. 2004. Water, Soil and Plant relationship. Astan Quds Razavi Publishing House, Mashhad, 470p (In Persian).
-    Amato, D., Recola, M., Li, N. and Toppinen, A. 2016. The use of species distribution model to predict the spatial distribution of deforestation in the western Brazilian Amazon. Ecological Modelling, 391: 250-259.
-    Attarod, P., Sadeghi, S.M.M., Dolatshahi, A., Rostami, F. and Zahedi Amiri, Gh. 2013. Investigation of Zagros Climatology. The first national conference on environmental hazards in Zagros, Khoram Abad, 30p (In Persian).
-    Attarod, P., Sadeghi, S.M.M., Sarteshnizi, F.T., Saroyi, S., Abbasian, P., Masihpoor, M., Kordrostami, F. and Dirikvandi, A. 2016. Effects of meteorological parameters and evapotranspiration on Zagros forests decline in Lorestan Province. Iranian Journal of Forest and Range Protection Research, 13(2): 98-114 (In Persian).
-    Beyranvand, A., Attarod, P., Tavakoli, M. and Marvie Mohadjer, M.R. 2015. Zagros forests decline, causes, implications and solutions. Iranian Journal of Forest and Range Quarterly, 106: 17-29 (In Persian).
-    Bigler, C., Braker, O.U., Bugmann, H., Dobbertin, M. and Rigling, A. 2006. Drought as an inciting mortality factor in Scots pine stands of the Valais. Switzerland. Ecosystems, 9: 330-343.
-    Breiman, L. 1984. Classification and regression trees. Wadsworth international group, belmont, CA, USA.
-    Breiman, I. 2001. Random forests. Machine Learning, 45: 5-32.
-    Busby, J.R. 1991. BIOCLIM – a bioclimate analysis and prediction system. Plant Protection Quarterly, Australia.
-    Carpenter, G., Gillison, A.N. and Winte, J. 1993. DOMAIN: a flexible modelling procedure for mapping potential distributions of plants, animals. Biodiversity Conservation, 2: 667-680.
-    Das, A.J., Battles, J., Van Mantgemd, P.J. and Stephenson, N.L. 2008. Spatial elements of mortality risk in old-growth forests. Ecology, 89: 1744-1756.
-    Das, A.J., Battles, J., Stephenson, N.L. and Van Mantgemd, P.J. 2011. The contribution of competition to tree mortality in old-growth coniferous forests. Forest Ecology and Management, 261: 1203-1213.
-    De Souza, R.A., and De Marko, P. 2014. The use of species distribution models to predict the spatial distribution of deforestation in the western Brazilian Amazon. Ecological Modelling, 391: 250-259.
-    Dolatshahi, A. 2014. Estimate of sensitivity of reference evapotranspiration to climate change in the vegetative zone of North Zagros. Master’s thesis, Department of Forestry and Forest Economics, University of Tehran, Tehran, 108p (In Persian).
-    Espadafor, M. Lorite, I.J., Gavilan, P. and Berengena, J. 2011. An analysis of the tendency of reference evapotranspiration estimates and other climate variables during last 45 years in Southern Spain. Agricultural Water Management, 98: 1045-1061.
-    Farber, O. and Kadmon, R. 2003. Assessment of alternative approaches for bioclimatic modelling with special emphasis on the Mahalanobis distance. Ecological Modeling, 160: 115-130.
-    Farmer, A. 1993. The effects of dust on vegetation-a review. Environmental Pollution, 79: 63-75.
-    Franklin, J. F., Shugart, H.H. and Harmon, M.E. 1987. Tree death as an ecological process. Bioscience, 37: 550-556.
-    Friedman, J.H. 1991. Multivariate adaptive regression splines. Annalas of Statistics, 19: 1–67.
-    Friedman, J.H. 2001. Greedy function approximation: a gradient boosting machine. Annalas of Statistics, 29: 1189–1232.
-    Fatahi, M. 1995. Wild Pistachio Ecology, Proceedings of the first national seminar (Pearl of Grean), Natural resources and animal sciences research centre of Ilam province, 26-62 (In Persian).
-    Gaziree, M.G. and Ebrahimi Rastaghe, M. 2003. Zagros Forestry. Tehran University Press, Tehran, 560p (In Persian).
-    Ghorbanli, M. 2002. Herbal geography. Samt publication, Tehran, 316p (In Persian).
-    Guarin, A. and Taylor, A.H., 2005. Drought triggered tree mortality in mixed conifer forests in Yosemite National Park, California, USA. Forest ecology and management, 218: 229-244.
-    Hastie, T., Tibshrani, R. and Buja, A. 1994. Flexible discriminant analysis by optimal scoring. Journal of the American Statistical Association, 89: 1255–1270.
-    Hamzehpour, M., Kia-daliri, H. and Bordbar, K. 2011. Preliminary study of manna oak (Quercus brantii Lindl.) tree decline in Dashte-Barm of Kazeroon, Fars Province. Iranian Journal of Forest and Poplar Research, 19(2): 352-363 (In Persian).
-    He. Z. and Lo, C. 2007. Modeling urban growth in Atlanta using logestic regression. Computers, Environment and Urban Systems, 31: 667-688.
-    Hong, H., Pradhan, B., Jebur, M.N., Bui, D.T., Xu. C. and Akgun, A. 2016. Spatial prediction of landslide hazard at the Luxi area (China) using support vector machines. Environmental Earth Science, 75: 40-55.
-    Hirzel, A.H. 2002. Ecological niche factor analysis: how to compute habitat suitability maps without absence data Ecology, 83: 2027-2036.
-    Khosh Kish, A., Aligani, B. and Hegazi Zade, Z. 2011. Synoptic Analysis of Dust in Lorestan Province. Journal of Applied Geosciences Research, 18(21): 91-110.
-    Lopez-Urrea, R., Martina desanta Olalla, F., Fabeiro, C. and Moratalla, A. 2006. Testing evapotranspiration equations using lysimeter observations in a semi-arid climate. Agricultural Water Management, 85: 15-26.
-    Mackee, B., Nolan, T., Dooesken, J. and Kleist, J. 1995. Drought monitoring with multiple timescales. Conference on Applied Climatology. Bostun, 15-20 January 1995.
-    Mahdavi, A., Mirzaee Zadeh, V., Nick nejad, M. and Karami, O. 2015. Investigation and prediction of decay of oak trees using logistic regression model (Case Study: Bierreh malekshahi-illam forests). Iranian Journal of Forest and Range Protection Research, 13(1): 20-32 (In Persian).
-    Marvi Mohajer, M.R. 2011. Silvics and Forestry. Tehran university press, Tehran, 420p (In Persian).
-    Mc Cullagh, P. and Nelder, J.A. 1989. Generalized linear models. Chapman and Hall. 511p.
-    Moravie, M.A. and Robert, A. 2003. A model to assess relationships between forest dynamics and spatial structure. Journal of Vegetation Science, 14: 823-834.
-    Nadi, M., Gamee, M., Bazr Afshan, G. and Ganat Rostami, S. 2012. Evaluation of Different Methods for interrogating Monthly and Annual Rainfall Data (Case study, Kuzestan Province). Natural Geagraphy Research, 44(4): 117-130 (In Persian).
-    O’Loingsigh, T., McTainsh, G.H., Tews, E.K., Strong, C.L., Leys, J.F., Shinkfield, P. and Tapper, N.J. 2014. The Dust Storm Index (DSI): A method for monitoring broadscale wind erosion using meteorological records. Aeolian Research, 12: 29-40.
-    Ozturk, M., Dogan, Y., Sakcali, M.S., Doulis, A. and Karam, F. 2010. Ecophysiological responses of some maquis (Ceratonia silique L. Olea oleaster Hoffm. & Link, Pistacia lentiscus and Quercus coccifera L.) plant species to drought in the east Mediterranean ecosystem. Journal of Environmental Biology, 31(1-2): 233-245.
-    Phillips, S.J., Anderson, R.P. and Schapire, R.E. 2006. Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190: 231–259.
-    Rosenblatt, F. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychology Revolution, 65: 386.
-    Rostami, F., Attarod, P., Sadeghi, S.S.M., Kavalry, M. and Zahedi Amiri, Gh. 2013. Changes in climatic factors and reference evapotranspiration in the Southern Zagros region. the First National Conference on Environmental Hazards in Zagros, Khoram Abad, 10p (In Persian).
-    Sharifan, M., Ghahraman, B., Alizadeh, A. and Mir Latifi, M. 2005. Evaluation of radiation and moisture methods for estimating reference evapotranspiration and air drying effects in Golestan province. Journal of Soil and Water Sciences, 19(2): 280-290 (In Persian).
-    Smit, B., Burton, I., Klien, R.J. and Wandel, J. 2000. An anatomy of adaptation to climate change and variability. Climatic Change, 45: 223-257.
-    Stockwell, D. and Peters, D. 1999. The GARP modeling system: problems and solutions to automated spatial predictions. Geoghraphic information science, 13: 143-158.
-    Thagheb Talebi, Kh., Sajedi, T. and Yazdian, Gh. 2004. A look at Iran’s forests. Publications of Forest and Rangeland Research Institute, Tehran, 56p (In Persian).
-    Thabeti, H. 1994. Forests, trees and shrubs of Iran. Yazd university press, Yazd, 875p (In Persian).
-    UNESCO, 1979. Map of the world distribution of arid regions: explanatory note. MAP technical notes 7, UNESCO: Paris, 54p.
-    Van Mantgemd, P.J., Stephenson, N.L., Byrne, J.C., Daniels, L.D., Franklin, J.F., Fule, P.Z., Harmon, M.E., Larson, A.J., Smith, J.M., Taylor, A.H. and Veblen, T.T. 2009. Widspread increase of tree mortality rates in the Western United States. Science, 5913(323): 521-524.
-    Vapnik, V. 1995. The nature of statistical learning theory. Springer, 188p.
-    Wang, Z., Lai, C., Chen, X., Yang, B., Zhao, S. and Bai, X. 2015. Flood hazard risk assessment model based on random forest. Journal of Hydrology, 527: 1130-1141.
-    Walther, G.R., Post, E., Convey, P., Menzel, A., Parmesan, C., Beebee, T.J.C., Fromentin, J.M., Hoeghguldberg, O. and Bairlein, F. 2002. Ecological Responses to Recent Climate Change. Nature, 416: 389-395.