برآورد حدود پراکنش مکانی گونه‌های گیاهی با روش شبکۀ عصبی‌مصنوعی در مراتع غرب تفتان

نویسنده

دانشگاه زابل

چکیده

پژوهش حاضر با هدف برآورد حدود پراکنش گونه‌های گیاهی و تهیۀ نقشۀ پیش‌بینی پراکنش گونه‌ها با روش پرسپترون چندلایه، در مراتع غرب تفتان در شهرستان خاش انجام شد. برای این منظور، بعد از شناسایی و تفکیک رویشگاه‌ گونه‌های مورد­بررسی، نمونه‌برداری از پوشش گیاهی به­روش تصادفی‌ـ منظم انجام شد. برای نمونه‌برداری از خاک در هر رویشگاه، شش نیمرخ حفر و از دو عمق 30-0 و 60-30 سانتی‌متری نمونه‌برداری شد. بعد از اندازه‌گیری خصوصیات خاک در آزمایشگاه و تهیۀ لایه‌های مربوط به خصوصیات فیزیوگرافی (شیب، جهت، ارتفاع)، زمین‌شناسی و خصوصیات فیزیکی‌ـ شیمیایی خاک با استفاده از زمین‌آمار و سیستم اطلاعات جغرافیایی، مدل‌سازی پراکنش رویشگاه گونه‌ها به­روش پرسپترون چندلایه انجام شد. بعد از انتخاب مدل پیش‌بینی بهینه برای هر رویشگاه، شبیه‌سازی احتمال حضور و عدم‌حضور گونه‌ها انجام شد. در مرحلۀ بعد، آستانۀ بهینه‌حضور به روش حساسیّت و اختصاصیّت برابر تعیین شد و مقدار تطابق نقشه‌های حاصل از مدل بهینۀ پیش‌بینی با نقشه‌های واقعی از طریق محاسبۀ شاخص کاپا بررسی شد. براساس مقادیر شاخص کاپا، نقشۀ پیش‌بینی حاصل از روش پرسپترون چندلایه برای رویشگاه Haloxylon persicum دارای تطابق خیلی‌خوب با نقشۀ واقعی پوشش گیاهی است. علاوه بر این، میزان تطابق برای رویشگاه‌های Artemisia aucheri، Artemisia sieberi و Amygdalus scoparia خوب و برای رویشگاه Zygophyllum eurypterum در سطح متوسط ارزیابی شد. این نتایج گویای آن است که روش پرسپترون چندلایه قادر است با استخراج قوانین حاکم بر داده‌ها و مدل‌سازی فرایندهای غیرخطی، مدل‌های پیش‌بینی دقیقی را ارائه کند. این امر می‌تواند منجر به پیش‌بینی صحیح حدود جغرافیایی پراکنش گونه‌های گیاهی شود و علاوه بر صرفه‌جویی در هزینه و زمان پژوهش‌ها، امکان موفقیت طرح‌های اصلاحی را نیز در مراتع افزایش دهد.

کلیدواژه‌ها


عنوان مقاله [English]

An Estimation of Spatial Distribution Domain of Plant Species Using Artificial Neural Networks in West Rangelands of Taftan

نویسنده [English]

  • Hossein Piri Sahragard
چکیده [English]

This study aimed to estimate of spatial distribution scope of plant species and preparation of predictive distribution maps of plant species using Artificial Neural Network (ANN) in Taftan west rangelands of Khash city. To this end, vegetation sampling was carried out by random-systematic method after identification and separation of plant species habitats. In order to sample the soil at each habitat, eight holes was drilled and samples were taken from 0-30 and 30-60 cm depths. Habitats distribution of plant species was modeled using multilayer perceptron after measurement of soil characteristic in the lab and providing of environmental variable maps including  physiographic characteristic (slope, aspect and elevation), geological formation and  soil physical and chemical properties using GIS and Geostatistics. Simulation of presence and absence probability was conducted after selection of optimal predictive model for each plant species. Then the optimal threshold was determined using equal sensitivity and specificity method and were examined the compliance between predicted and actual maps by calculating kappa index. Based on Kappa value, the agreement of predicted and actual map was very good for the habitats of Haloxylon persicum .Moreover, predictive maps of Artemisia aucheri, Artemisia sieberi and Amygdalus scoparia habitats have good agreement with actual maps of these species. As well as, correspondence of predictive and actual map of Zygophyllum eurypterum was assessed at moderate level. These results indicate that multilayer perceptron method (MLP) is capable to provide precise prediction models through data mining rules and modeling of nonlinear processes. Besides cost  and  time  saving of  research, this can lead to precise  prediction of  geographic  scope of  plant  habitat  distribution, as  a  result will increase  success possibility of rehabilitation  plans  in  the  rangelands.

کلیدواژه‌ها [English]

  • Spatial Distribution
  • Multilayer perceptron
  • Presence Optimal Threshold
  • Kappa Index
  • West Rangelands of Taftan
Abbasi, M., Zare Chahouki, M.A. 2014. Modeling of potential habitat for Stipa barbata and Agropyron intermedium species using artificial neural network model in rangeland of Central Taleghan. Journal of Renewable Natural Resources 5 (2): 45-56. 2. Aertsen, W., Kint, J.V., Muys, B. 2010. Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests. Ecological Modeling 221: 1119–1130. 3. Basheer, I. A., Hajmeer, M. 2000. Artificial neural networks: fundamentals, computing, design, and applivation, Journal of Microbiological Methods 43: 3-31. 4. Bedia, J., Busque, J., Gutierrez, J.M. 2011. Predicting plant species distribution across an alpine rangeland in northern Spain. A comparison of probabilistic methods. Applied Vegetation Science 14: 415–432. 5. Carl, J., Ku hn, I. 2007. Analyzing spatial autocorrelation in species distributions using gaussian and logit models. Ecological Modelling 207: 159-170. 6. Cochran, WG. 1954. The combination of estimates from different experiments. Biometrics 10:101-129. 7. Ebrahimi, M., Masoodipour, A., Rigi, M. 2015. Role of Soil and Topographic Features in Distribution of Plant Species (Case study: Sanib Taftan Watershed), Ecopersia 3 (1): 917-932 Ekhtesasi, M.R. 2003. Determination of the minimum density of Haloxylon seedling in order to design tree windbreaks and wind erosion control in central Iran. Proceedings of Nationalconference of the Haloxylon and planting of Haloxylon in Iran, Kerman, 2-3 Pp. 9. Faghih, H. 2009. Evaluation of artificial neural network and genetic algorithm optimization to estimation of monthly precipitation data (Case Study: Kurdistan Region). Journal of Science and Technology of Agriculture and Natural Resources, Soil and Water Science 14 (51): 42-27. 10. Fielding, A.H., Bell, J. 1997. A Review of Methods for the Assessment of Prediction Errors in Conservation Presence/Absence Models, Environment Conservation Journal, 24; 38-49. 11. Franklin, J. 1995. Predictive Vegetation Mapping: Geographic Modelling of Biospatial Patterns in Relation to Environmental Gradients, Progress in Physical Geography 19(4): 474-499. 12. Goodarzi, Gh. R., Sagheb-Talebi, Kh., Ahmadloo, F. 2012. The study of effective factors on Almond (Amygdalus scoparia Spach.) distribation in Markazi province. Iranian Journal of Forest 4(3): 209-220. 13. Guisan, A., Theurillat, J. 2000. Equilibrium modeling of alpine plant distribution: how far can we go? Phytocoenologia 30:353-384. 14. Hagan, M. T., Menhaj, M. B. 1994. Training feed forward networks with the Marquardt algorithm. IEEE Trans on Neural Networks 5: 989-993. 15. Heaton, J. 2010. Programming Neural Networks with Encog2 in C#. Heaton Research, Inc. 16. Hilbert, D.W., Ostendorf, B. 2001. The utility of artificial neural networks for modeling the distribution of vegetation in past, present and future climates. Ecological Modelling 146:311-327. 17. Hirzel, A., Guisan, A. 2002: Which is the optimal sampling strategy for habitat suitability modelling. Ecological Modelling 157:331–41. 18. Hosseini, S. Z., Kappas. M., Zare Chahouki. M. A., Gerold, G., Erasmi. S., Rafiei Emam, A. 2013. Modelling potential habitats for Artemisia sieberi and Artemisia aucheri in Poshtkouh area, central Iran using the maximum entropy model and geostatistics, Ecological Informatics 18, 61-68. 19. Ingram, J.C., Dawson, T.P., Whittaker, R.J. 2005. Mapping tropical forest structure in southeastern Madagascar using remote sensing and artificial neural networks. Remote Sensing of Environment 94:491-507. 20. Jafari Haghighi, M. 2003. Methods of soil analysis: sampling and Physical and chemical analysis with emphasis on the theoretical and practical importance. Tehran University Press, 236 pages. 21. Lawler, J.J., White, D., Neilson, R. P., Blaustein, A. R. 2006. Predicting climate-induced range shifts: model differences and model reliability. Global Change Biology 12:1568–1584. 22. Liu, C., Berry, P. M., Dawson, T. P., Pearson, R.G. 2005. Selecting thresholds of occurrence in the prediction of species distributions, Ecography 28:385-393. 23. Mahmoudi, A.A., Zahedi, Gh., Etemad, V. 2012. The investigation on the relationship between soil physical and chemical properties and succulence of natural and planted saxaul (Haloxylon spp) (Case study: Hosseinabad plain, Southern Khorasan province). Iranian Journal of Forest 4(4): 289-299. 24. Manel, S., Dias, J. M., Ormerod, S.J., 1999. Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river bird. Ecological Modelling 120: 337-347. 25. Melesse, A.M., Hanley, R.S. 2005. Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modelling 189: 305-314. 26. Menhaj, M.B. 2002. Functional Neural Networks. Amirkabir University of Technology Publisher. Second edition, 715p. 27. Monserud, R. A., Leemans, R.1992. Comparing global vegetation maps with the Kappa statistic. Ecological Modelling 62: 275-293. 28. Pearce, J., Ferrier, S. 2000. Evaluating the predictive performance of habitat models developed using logistic regression. Ecological Modelling 133:225–45. 29. Pearson, R. G. 2007. Species distribution modeling conservation educators and practitioners. Synthesis. New York: American Museum of Natural History. 30. Pearson, R., Dawson, T. P., Liu, C. 2004. Modelling species distributions in Britain: a hierarchical integration of climate and land-cover data. Ecography 27: 285-298. 31. Piri sahragard, H. 2014. Evaluation of statistical models efficiency to predict the distribution of plant Species, (Case study: Qum Province Rangelands), PhD thesis of range management, faculty of natural resources, University of Tehran, 157 pages. 32. Piri sahragard, H., Zare Chahouki M.A., H. Azarnivand. 2014. Modelling of plant species distribution in the Hoze sultan west rangelands of by Logistic regression analysis. Journal of range management 1 (1): 15-25. 33. Piri sahragard, H., Zare Chahouki, M.A. 2015. An evaluation of predictive habitat models performance of plant species in Hoze soltan rangelands of Qom province. Ecological Modelling 309-310: 64-71. 34. Piri sahragard, H., Zare Chahouki, M. A., Azarnivand, H. 2015. Application of logistic regression in preparation of predictive distribution map of plant species habitats (Case study: Khalajestan rangelands of Qum province), Rangeland journal 9 (3): 222-234. 35. Piri sahragard, H., Zare Chahouki, M.A., Azarnivand, H. 2015. Modelling of plant species distribution in arid regions using Artificial Neural Networks (ANN). (Case Study: Hoze Soltan rangelands of Qom province). Desert Management 4: 27-40. 36. Piri sahragard, H., Zare Chahouki M. A. 2016. Comparison of logistic regression and machine learning techniques in prediction of habitat distribution of plant species. Range Management & Agroforestry 37 (1) : 21-26. 37. Piri Sahragard, H., Zare Chahouki, M.A. 2016. Modeling of Artemisia sieberi Besser Habitat Distribution Using Maximum Entropy Method in Desert Rangelands, Journal of Rangeland Science 6(2): 93- 101. 38. Rigi, M., Naruie, A. 2007. A plan on desert management in Khash plant area, the Department of Natural Resources and Watershed Sistan and Baluchestan, 104 Pp. 39. Segurado, P., Araújo, M. 2004. An evaluation of methods for modelling species distributions. Journal of Biogeography 31,15: 55–69. 40. Tavakoli Neko, H., Pourmeydani, A., Adnani, S.M., Sagheb-Talebi, Kh. 2012. Impact of some important ecological factors on presence of mountain Almond (Amygdalus scoparia Spach.) in Qom province, Iran. Iranian Journal of Forest and Poplar Research 19 (4): 523-542. 41. Zare Chahouki, M.A. 2006. Modelling the spatial pattern of plant species in arid and semi-arid rangelands (Case study: Poshtkouh region of Yazd province), Ph.D. thesis. 180 P. 42. Zare Chahouki, M. A., Khalasi Ahvazi, L., Azarnivand, H. 2012. Comparison of three modeling approaches for predicting plant species distribution in mountainous scrub vegetation (Semnan rangelands, Iran), Polish Journal of Ecoloy 60 (2): 105-117. 43. Zare Chahouki, M. A., Piri Sahragard H, Naghilou, M. 2016. Determination of Occurrence Optimal Thresholds in the Predictive Models of Plant Species Distribution (Case study: Rangelands of Nir region of Yazd province), Desert Ecosystem Engineering Journal 5(10): 1-12.