پهنه‌بندی پراکنش مکانی نوعی آویشن (Thymus kotschianus)و بوماران Achilla millefolium) )با استفاده از شبکه عصبی مصنوعی (مطالعه موردی: مراتع دونا استان مازندران)

محورهای موضوعی : پهنه بندی گیاهی

زینب بحرینی ¹ (دانشجوی دکتری علوم مرتع، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران.)
زینب جعفریان ² (استاد دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران. * (مسوول مکاتبات))
مریم شکری ³ (استاد دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران.)

تاریخ دریافت : 1395/10/27 تاریخ پذیرش : 1396/03/24 تاریخ انتشار : 1399/11/01

کلید واژه: گونه‌های دارویی, شبکه پرسپترون چند لایه, منحنی ROC, مراتع دونا,

چکیده مقاله :

زمینه و هدف: هدف از این پژوهش، استفاده از مدل شبکه عصبی مصنوعی در تهیه نقشه پراکنش مکانی گونه های نوعی آویشن وبو مادران در مراتع دونا استان مازندران است. روش بررسی: نمونه برداری از پوشش گیاهی به روش طبقه بندی تصادفی در 29 واحد همگن انجام شد. در هر واحد همگن، 3 نمونه خاک نیز از عمق 30-0 سانتی متری برداشت شدند. در پژوهش حاضر، از 20 عامل محیطی به عنوان متغیر مستقل و داده های مربوط به حضور گونه های گیاهی مطالعه شده به عنوان متغیر وابسته استفاده گردید. برای تهیة نقشه پیش بینی مکانی گونه ها، اطلاعات محیطی در GIS تبدیل به نقشه شده و با استفاده از روش نسبت فراوانی هر کدام از آن ها کلاسه بندی شدند. در این پژوهش از شبکه پرسپترون چند لایه، متداول ترین شبکه های عصبی مصنوعی پیش خور، استفاده گردید. ساختار بهینه شبکه عصبی مصنوعی، 1، 20، 20 تعیین شد. خروجی به دست آمده از شبکه در نرم افزار GIS تبدیل به نقشه های پهنه بندی گونه های گیاهی با 4 پهنه عدم حضور، حضور کم، حضور متوسط و حضور زیاد شد. ارزیابی مدل به دو روش منحنی ROC و ضریب کاپا انجام شد. یافته ها:با استفاده از روش منحنیROC، مقدار AUC برای گونه بومادران برابر 8/96، و برای گونه نوعی آویشن برابر 7/84 شد که نشان دهندة ارزیابی عالی و خیلی خوب مدل در پیش بینی است. بحث ونتیجه گیری: ارزیابی به روش ضریب کاپا نشان داد که این ضریب برای گونه بومادران، و گونه نوعی آویشن، به ترتیب برابر 89/0 و 76/0 بود که نشان دهندة ارزیابی بسیار خوب و خوب مدل است.

چکیده انگلیسی:

Background and Objective:The purpose of this study was to map the spatial distribution of common yarrow(Achilla millefolium)and thyme (Thymus kotschianus) using artificial neural network model in rangelands Donna, Mazandaran Province. Method:Sampling was carried out with equal random classification in 29 homogenous units. In each unit, 3 soil samples were harvested from depth of 0-30 cm. In this study, 20 environmental factors were the independent variables and the presence of plant species were the dependent variable. For the preparation spatial distribution map of the species, environmental data were converted to maps in GIS. Then each of these factors was classified using the frequency. In this research, network Multilayer Perceptron that is the most common feed forward neural network was used. Optimal structure for the network was determined 1, 20, and 20. Then distribution maps of studied species were prepared with 4 class absence and low presence, medium presence and high presence in the GIS software. Models were evaluated using ROC curves and Kappa coefficient. Findings:AUC were 96.8 and 84.7 for the species Achilla millefolium and Thymus kotschianus was, respectively  that indicates models are excellent or very good for the prediction. Discussion and Conclusion: Also kappa coefficient were calculated as 89.0 and 76.0 for Achilla millefolium and Thymus kotschyanus,  respectively which  indicate very good and good prediction.    

منابع و مأخذ:

1. Anderson, R.P, Lew, D., Peterson, A.P., 2003. Evaluating predictive models of species distributions: criteria for selecting optimal models. Ecological Modeling, Vol. 162, pp. 211–232.


2. Burke, A., 2001. Classification and ordination of plant communities of the Nauklaft Mountain, Namibia. Journal of Vegetation Science, 12, pp. 53-60.


3. Constantin, M., Bednarik, M., Jurchescu, C., Vlaicu, M., 2010. Landslide susceptibility assessment using the bivariate statistical analysis and index of entropy in the Sibiciu Basin (Romania),­ Environmental ­Earth Science, 10p.                                                                                                                                                                                      


4. Drake, J. M, Randin, C., Guisan, A., 2006. Modeling ecological niches with support vector machines. Journal of Applied Ecology, Vol. 43, pp. 424–432.


5. Ermini, L., Catani, F., Casagli, N., 2005. Artificial neural networks a applied to landslide susceptibility assessment. Geomorphology, Vol. 66, pp. 327-343.


6. Elith, J, Leathwick, J. R., 2009. Species distribution models: ecological explanation and prediction across space and time. Annual Review of Ecology Evolution and Systematic, Vol. 40, pp. 677–697.


7. Fielding, A. H, Bell, J. F., 1997. A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental Conservation, Vol. 24, pp. 38–49.


8. Guisan, A., Thuiller, W., 2005. Predicting species distribution: offering more than simple habitat models. Ecology Letters, Vol. 8, pp. 993–1009. 


9. Guisan A, Zimmermann N. E., 2000. Predictive habitat ­distribution models in ecology. Ecological Modeling, Vol. 135, pp. 147–186.


10. Ghorbani, M. A., 2009.  "Water Management Software, Publication noorpardazn. (In Persian)  


11. Gomez H., Kavzoglu T., 2005. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin. Venezuela Engineering Geology, 78, pp. 11-27.


12. Govindaraju, R.S., 2000. Artificial neural networks in hydrology II: hydrologic applications. Journal of Hydrologic Engineering, Vol. 5, pp. 124-137.


13. Irmak, A, Jones, J. W., Batchlor, W. D., Irmak, S., Bootek, K. J, and Paz, J. O., 2006. Artificial neural network model as a data analysis tool in precision farming. American Society of Agricultural and Biological Engineers, 49, pp. 2027−2037.


14. Jori MH, Mahdavi M., 2010. Applications identification of rangeland plants. 434p. (In Persian)


15. Komak M. A., 2006. Landslide susceptibility model using the Analytical Hierarchy Process method and multivariate statistics in perialpine Sloveni. Geomorfology, Vol. 74, pp. 17-28.


16. Lee, S., Ryu, J. H, Lee, M., Wos, J. S., 2003. Use of artificial neural networks for analysis of the susceptibility to landslide at Boun, korea. Environmental Geology, Vol. 44, pp. 820-833.


17. Lee, S, Ryu J. H, Won, J. S. park, H., 2004. Determination and application of the weights for landslide susceptibility mapping using an artificial neural network. Eng Geo, 71, pp. 289-302.


18. Lee, S, Sambath, T., 2006. Landslide susceptibility mapping in the Damarei Romel area, Cambodia using frequency ratio and logistic regression models. The journal of Environmental Geology,Vol. 50, pp. 847-855.


19. Lee, S., Ryu, J. H., Lee, M., Won, J. S., 2006. The application of artificial neural networks to landslide susceptibility mapping at Jang hung korea. Mathematical Geology, Vol. 38, pp. 199-207.


20. Landis, J. R, Koch, G. C., 1977. The measurement of observer agreement for categorical data. Biometrics, Vol. 33, pp. 159-174.


21. Melesse, A. M., Hanley, R. S., 2005. Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modeling, Vol. 189, pp. 305–314.


22. Menhag, M. B., 2008. Principles of Neural Networks (Computational Intelligence). First vol. Publication Center Amirkabir University of Technology, 715 p.


23. Malhado, A.C, Petrere, J.M., 2004. Behavior of dispersion indices in pattern detection of a population of Angico, Andenathera peregrine. Barzilian Journal Biology, Vol. 64, pp. 243-249.


24. Neuhäuser, B., Terhorst, B., 2007. Landslide susceptibility assessment using “weights-of-evidence” applied to a study area at the Jurassic escarpment (SW- Germany). Geomorphology, Vol. 86, pp. 12–24.


25. Nefeslioglu, H. A., Duman, T. Y., Durmaz, S., 2008. Landslide susceptibility mapping for a part of tectonic Kelkit Valley (Easten Black Sea Region of Turkey). Geomorphology, Vol. 94, pp. 401-418.


26. Oysia, N., Khalili Mosavi, A., Mazandarni, M., Bayat, H., Borhani, G., 2013."The most important ecological needs, avtofarmacology of medicinal herbs in the southeast of Golestan province," Journal of Ecophytochemistry of Medicinal Plants, 1(1), pp. 65-83.


27. Piccinini C., 2011. Assessing the impact of climate change on plant distributions using Artificial Neural Networks .PhD. Thesis, Kingston University.


28. Paruelo, J. M., Tomasel, F., 1997. Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models. Ecological Modeling, Vol. 98, pp. 173-186.


29. Paradhan, B., Lee, S., 2010. Landslide susceptibility assessment and factor effect analysis: back propagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modeling. Environmental modeling & Software, pp. 747-759.


30. Rakee B, Khamechian M, Abdolmalaki P, Giahchi P., 2007. Application of artificial neural network landslide hazard zonation (Case study: Area Sefidar Gale in Semnan province). Tehran University Journal of Science, Vol. 33, pp. 57-64.


31. Van Western, C. J., 2002. Use of weights of evidence modeling for landslide susceptibility mapping. 21 p.


32. Rostampour, M., 2008. "Study of the Relationship Between Vegetation and Environmental Factors in Cairo Mountain Range", Master's Thesis, Faculty of Natural Resources, Tehran University, 180 p. (In Persian)  


33. Yilmaz, I., 2009. Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison (A case study from Kat Landslides (Tokat-Turkey). Computers & Geosciences, Vol. 35, pp. 1125-1138.


34. Zare Chahoki, 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 Ecology, Vol. 60 , pp. 277-289. (In Persian)


35. Zhou L, Yang X., 2008. Use of neural networks for land cover classification from remotely sensed imagery. The International Archives of the Photogrammetric Remote Sensing and Spatial Information Sciences, Vol. XXX VII. Part B7.


36. Zhu ­C., Wang X., 2009. Landslide susceptibility mapping: A comparison of information and weights-of evidence methods in Three Gorges Area. International Conference on Environmental Science and Information Application Technology, Vol. 187, pp. 342-346.

3. Bahlar, M., Khoshsokhan, F., Fatahimoghadam, M.R., Poormeidani, A., 2013. "Evaluation of morphological diversity and essential oil yield in some Thymus kotschyanus Boiss. & Hohen populations", Iranian Journal of Horticultural Science, 44(2), pp. 119-128.


4. Cheyyann, R., 2007 "Estimation of electrical conductivity using artificial neural network method", Journal of Agriculture and Biology, Vol. 9, No. 6.

10. Farajpour, M.,  2009. "Evaluation of the genetic diversity of Achillea millefolium with ISSR markers", Ecology and systematic biochemistry, No. 43. (In Persian)

15. Ghani, A., Azizi, M., Farali, T., 2009. "Evaluation of Ornamental Potentials of Five Wild Achillea Species", Journal of Horticultural Science, 23(2), pp. 261-277. (In Persian)

19. Karimzadeh, A., Jafarian, Z., Shokri, M., Akbarzade, M., 2010, "Analysis of Relationship between Vegetation and Environmental Factors Using Multivariate Analysis (Case Study: Semnan Semnan Province)", Master's Thesis, University of Agricultural Sciences and Natural Resources, Sari, 143p. (In Persian)

21. Kia, F., 2011. "The Relationship between Distribution of Grass Seed Species and Some Environmental Factors in Golestan Province", Journal of Rangeland, Vol. 5, No. 3. (In Persian)


22. Khadem Al-Hosseini, Z., Shokri, M., S. H. Habibian., 2005. The Relationship Between Vegetation Communities and Environmental Factors in Bonab Range, Fars Province, Journal of Rangeland, Vol. 1, No. 3. pp. 222-236. (In Persian)

28. Mirdeilami, Z., Heshmati, G. A., Mazandarani, M., Barani, H., 2015. Quantitative and qualitative study of chemical compounds of essential oil of flowering shoots of medicinal plant Achillea millefolium L. in Maravehpeh area, Golestan province,7(1), pp. 34-41. (In Persian)

38. Pourghasemi, Hamid Reza, "Evaluation of landslide hazard by fuzzy method in Haraz watershed", Master thesis, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares Nos., 2007, p. 93. (In Persian)

40. Rahmati, Z., Tarkesh, M., Poormanafi, S., Vahabbi, M. R., 2015. Determination of the potential habitat of Ferula ovina Boiss species using Artificial Neural Network in Fereydoun-Shahr area of Isfahan, Applied Ecology, 4(11), pp. 35-41. (In Persian)

43. Salardini, A.A.,2006. The Relationship between Soil and Plant, Tehran University Press. (In Persian)