پیش‌بینی پراکنش رویشگاه گونۀSeidlitzia rosmarinus در مراتع شرق سمنان با استفاده از مدل شبکه عصبی مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، دانشکده مرتع و آبخیزداری، دانشگاه کشاورزی و منابع طبیعی گرگان، ایران

2 استاد، گروه احیاء مناطق خشک و کوهستانی، دانشکده منابع طبیعی دانشگاه تهران، کرج، ایران

چکیده

شبکه عصبی مصنوعی، ساختارهای پردازش اطلاعاتی جدیدی هستند که از روش‌های مخصوص شبکه‌های عصبی بیولوژیک استفاده می‌کنند. هدف از این مطالعه مدل‌سازی پراکنش گونه Seidlitziarosmarinus در مراتع شمال شرق سمنان با استفاده از مدل شبکه عصبی است. بدین منظور برای نمونه‌برداری از پوشش گیاهی در هر تیپ رویشی، 3 ترانسکت 750 متری مستقر و در هر ترانسکت 15 پلات با فواصل50 متر مستقر شد. نمونه‌برداری از خاک با توجه به مرز تفکیک افق‌ها در منطقه و نوع گیاهان موجود از دو عمق 20-0 و 80-20 سانتی‌متر انجام شد. برای تهیۀ نقشۀ پیش‌بینی پراکنش گونه‌های گیاهی، به فراهم کردن لایه‌های عوامل محیطی مورد استفاده در مدل نیاز است. برای نقشه‌بندی خصوصیات خاک، روش زمین‌آمار براساس مدل پیش‌بینی بدست‌آمده برای گونه S.rosmarinus (روش ANN) استفاده شد. برای اجرای مدل شبکه عصبی، الگوریتم پس انتشار خطا با شبکه طراحی شده پرسپترون سه لایه‌ای با ساختار 1-10-7  و دارای هفت نرون در لایه ورودی، ده نرون در لایه میانی و یک نرون در لایه خروجی استفاده شد. میزان تطابق نقشۀ تهیه شده با نقشۀ واقعیت زمینی نیز با استفاده از ضریب کاپا محاسبه شد که نشان‌دهنده تطابق خیلی خوب بود (ضریب کاپای 72/0). نتایج نشان داد گونه S.rosmarinus در مناطق با اسیدیته 3/8-1/8، هدایت الکتریکی 26/0-22/0 دسی‌زیمنس بر متر، بافت لومی-شنی و در ارتفاع 1750-1600 متر از سطح دریا پراکنش دارد و با میزان اسیدیته و آهک رابطه مستقیم دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Preparing the distribution of Seidlitzia rosmarinus in Semnan East rangeland using ANN model

نویسندگان [English]

  • Leila Khalasi Ahvazi 1
  • Mohammad ali zare chahouki 2
چکیده [English]

Artificial Neural Network (ANN) is new information processing structures that uses special methods for biological neural networks. The main purpose of this study was to modeling of Seidlitzia rosmarinus distribution in northeast rangelands of Semnan by ANN model. For this purpose, vegetation sampling was carried out in each vegetation type along three transects of 750 m, on which 15 plots were established with an interval of 50 m. Soil samples were taken from two depths of 0-20 cm and 20-80 cm in starting and ending points of each transect. To provide the prediction map of plant species distribution, different layers of environmental factors used in the model are required. The geostatistics method was applied for mapping soil properties based on the prediction model obtained from ANN method for S. rosmarinus. The back-propagation neural network with three-layer- perceptron network was designed to generate the ANN model and seven neurons in the input layer, ten neurons in the hidden layer, and one neuron in the output layer were used. The accuracy of the prediction map was tested with actual vegetation maps and the Kappa coefficient was calculated to be 72%, indicating a very good agreement. Results showed that this species is distributed in rangelands with a pH of 8.1-8.3, an EC 0.22-0.26 dS/m, in a silty-sandy textured soil, and an altitude of 1600-1750 meters. it is highly correlated with lime and pH in two depths.

کلیدواژه‌ها [English]

  • Artificial Neural Networks
  • Sedlitzia rosmarrinus
  • Back propagation
  • actual vegetation map
  • Kappa coefficient
-پیری صحراگرد، ح.، 1392. ارزیابی کارایی مدلهای آماری برای پیش بینی پراکنش گونه های گیاهی (مطالعه موردی: مراتع استان قم. رساله دکتری، دانشکده منابع طبیعی، دانشگاه تهران، کرج.

-حسنی پاک،ع.ا.، 1377. زمین آمار، انتشارات دانشگاه تهران، ایران، 314ص

-خلاصی اهوازی، ل.، زارع چاهوکی، م.، آذرنیوند، ح. و سلطانی گردفرامرزی، م.، 1390. مدل‌سازی مطلوبیت رویشگاه Eurotiaceratoides (L.) C.A.M.با کاربرد روش تحلیل عاملی آشیان بوم‌شناختی (ENFA) در مراتع شمال شرق سمنان. مرتع، 5 (4): 373-362.

-کروری، ع.ا.، خوشنویس، م.، 1379. مطالعات اکولوژی و زیست محیطی رویشگاه‌های ارس ایران، انتشارات موسسه تحقیقات جنگلها و مراتع، ایران، 208ص.

-زارع چاهوکی، م. ع.، زارع ارنانی، م.، زارع چاهوکی، ا. و خلاصی اهوازی، ل.، 1389.کاربرد روش‌های آمار مکانی در مدل‌های پیش‌بینی رویشگاه گونه‌های گیاهی. خشک‌بوم، 1 (1): 24-13

-Anderson, J. A., 2003. An Introduction to neural networks. Prentice Hall

-Abd El-Ghani M. and Wafaa M., 2003. Soil-vegetation relationships in a coastal desert plain of southern Sinai, Egypt. Journal of Arid Environment, 55(4): 607-628.

-Alemi, M. H., Azari. A. and Nielson, D. R., 1980. Kiriging and univarate modeling of a spatial correlate data. Soil Tecnology, 1: 133-147

-Almeida, J. S., 2002. Predictive non-linear modeling of complex data by artificial neural networks. Current Opinion in Biotechnology, 13: 72-6.

-Barbet-Massin, M., Rome, Q., Muller, F., Perrard, A., Villemant, C. and Jiguet, F., 2013. Climate change increases the risk of invasion by the yellow-legged hornet. Biology and Conservation, 157: 4–10.

-Báez, J. C., Estrada, A., Torreblanca, D. and Real, R., 2012. Predicting the distribution of cryptic species: the case of the spur-thighed tortoise in Andalusia (southern Iberian Peninsula). Biodiversity and Conservation, 21: 65–78.

-Bourg, N. A., McShea, W. J. and Gill, D. E., 2005. Putting a CART before the search: successful habitat prediction for a rare forest herb. Ecology, 86: 2793–2804.

-Brambilla, M., Bassi, E., Ceci, C. and Rubolini, D., 2010a. Environmental factors affecting patterns of distribution and co-occurrence of two competing raptor species. Interactive Biodiversity Information System, 152: 310–322.

-Brambilla, M., Casale, F., Bergero, V., Bogliani, G., Crovetto, G.M., Falco, R., Roati, M. and Negri, I., 2010b. Glorious past, uncertain present, bad future? Assessing effects of land-use changes on habitat suitability for a threatened farmland bird species. Biodiversity and Conservation, 143: 2770–2778.

-Brambilla, M. and Ficetola, G. F., 2012. Species distribution models as a tool to estimate reproductive parameters: a case study with a passerine bird species. Journal of Animal Ecology, 81:781–787.

-Brambilla, M. and Gobbi, M., 2014. A century of chasing the ice: delayed colonisation of ice-free sites by ground beetles along glacier forelands in the Alps. Ecography, 37: 33–42

-Cairns, D. M., 2001. A comparison of methods for predicting vegetation type. Plant Ecology, 156: 3–18

-Chamberlain, D. E., Negro, M., Caprio, E., Rolando, A., 2013. Assessing the sensitivity  of alpine birds to potential future changes in habitat and climate to inform management strategies. Biodiversity and Conservation, 167: 127–135.

-Cohen, J., 1960. A Coefficient of Agreement of Nominal Scales, Educational and Psychological Measurement, 20: 37–46.

-Cross, S. S., Harrison R. F., Kennedy R. L., 1995. Introduction to neural networks. Lancet, 346:1075-9

-Deng, J., Chin W., Wen, C. H. and Wen, P., 2008. "Back-Propagation Neural Network based Importance Performance Analysis for Determining Critical Service Attributes", Expert System with Applications, 34: 1115- 1125

-Elith, J., Phillips, S. J., Hastie, T., Dudık, M., Chee, Y. E. and Yates, C. J., 2011. A statistical explanation of MaxEnt for ecologists. Diversity and Distributions, 17: 43–57.

-Ficetola, G. F., Maiorano, L., Falcucci, A., Dendoncker, N., Boitani, L., Padoa-Schioppa, E., Miaud, C. and Thuiller, W., 2010. Knowing the past to predict the future: land-use change and the distribution of invasive bullfrogs. Global Change Biology, 16: 528–537.

-Fielding, A. H. and Bell, J. F., 1997. A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmenal Conservation, 24: 38–49.

-Fouquet, A., Ficetola, G.F., Haigh, A. and Gemmell, N., 2010. Using ecological niche modelling to infer past, present and future environmental suitability for Leiopelma hochstetteri, an endangered New Zealand native frog. Biodiversity and Conservation, 143: 1375–1384.

-Giannini, T. C., Chapman, D. S., Saraiva, A. M., Alves-dos-Santos, I., Biesmeijer, J.C., 2013. Improving species distribution models using biotic interactions: a case study of parasites, pollinators and plants. Ecography, 36: 649–656.

-Guisan, A. and Zimmermann, N. E., 2000. Predictive habitat distribution models in ecology. Ecological Modeling, 135: 147–186.

-Graham, C. H., Ferrier, S., Huettman, F., Moritz, C. and Peterson, A. T., 2004a. New developments in museum-based informatics and applications in biodiversity analysis. Trends Ecology and Evolution, 19: 497–503.

-Hirzel, A. H. and Hausser, J., Chessel, D. and Perrin, N., 2002. Ecological Niche Factor Analysis: How to compute habitat-suitability maps without absence data? Ecology, 73(22): 2027-2036

-Hortal, J., Roura-Pascual, N., Sanders, N. J. and Rahbek, C., 2010. Understanding (insect) species distributions across spatial scales. Ecography, 33: 51–53.

-Hsu, K., Gupta, H. V. and Sorooshian, S., 2003. Artificial neural networks modeling of rainfall-runoff process. Water Resources Research, 13(10): 2517-2530

-Jianbing, W., Alexandre, B. and Tuanfeng Z., 2008. A SGeMS code for pattern simulation of continuous and categorical variables: FILTERSIM. Computers & Geosciences, 34 (12):1863-1876.

-Ke´ry, M., 2010. Introduction to WinBUGS for ecologists – a Bayesian approach to regression, ANOVA, mixed models and related analyses. Academic Press, Burlington, MA.

-Khalasi Ahvazi, L., Zare Chahouki, M. A. and Azarnivand, H., 2011. Environmental factors effects on distribution of vegetation types in Daryan Rangelandes of Iran. Dryland Ecology Conference

-Liu, C., Berry, P. M., Dawson, T. P., and Pearson, R. G., 2005. Selecting thresholds of occurrence in the prediction of species distributions. Ecography, 28: 385–393

-Manel, S., Dias, J. M. and Ormerod, S. J., 1999. Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: as case study with a Himalayan river bird. Ecological Modeling, 120: 337–347.

-Mi, C., Yang J., Li S., Zhang X. and Zhu D., 2010. Prediction of accumulated temperature in vegetation period using artificial neural network. Mathenatic Computer Modeling. 51: 1453–1460.

-Moisen, G. and Frescino, T., 2002. Comparing five modelling techniques for predicting forest characteristics. Ecological Modeling, 157 (2–3): 209–225.

Monserud, R. A. and Leemans, R., 1992. Comparing global vegetation maps with the Kappa statistic. Ecological Modeling, 62: 275–293.

-Paola, J. D. and Schowengerdt, R. A., 1993. A review and analysis of neural networks for classification of remotely sensed multispectral imagery. Research Institute for Advanced Computer Science, NASA Ames Research Center Tech. Rep., 93.05 (NASA-CR-194291),

-Paola, J. D. and Schowengerdt, R. A., 1995. A detailed comparison of backpropagation neural network and maximumlikelihood classifiers for urban land use classification. IEEE Trans. Geosci. Remote Sensing, 33: 981–996.

-Peterson, A. T., Soberón, J. and Sánchez-Cordero, V., 1999. Conservatism of ecological niches in evolutionary time. Science, 285: 1265–1267.

-Özesmi U., Tan C. O., Özesmi S. L. and Rob-ertson R. L., 2006. Generalizability of artificial neural network models in ecological applications: Predicting nest occurrence and breeding success of the red-winged blackbird Agelaius phoeniceus. Ecological Modeling, 195: 94–104.

-Quetglas, A., Francesc Ordines and Beatriz Guijarro, J., 2010. The Use of Artificial Neural Networks (ANNs) in Aquatic Ecology. Artificial Neural Networks – Application 27: 567-586

-Robertson, M. P., Caithness, N. and Villet, M. H., 2000. A PCA-based modelling technique for predicting environmental suitability for organisms from presence records. Diversity and Distributions, (7): 15–27.

-Robertson, M. P., Peter, C. I., Villet, M. H., and Ripley, B. S., 2003. Comparing models for predicting species’ potential distributions: A case study using correlative and mechanistic predictive modeling techniques. Ecological Modeling, 164: 153–167.

-Raxworthy, C. J., Martinez-Meyer, E., Horning, N., Nussbaum, R. A., Schneider, G. E., Ortega-Huerta, M. A. and Peterson, A. T., 2003. Predicting distributions of known and unknown reptile species in Madagascar. Nature, 426: 837–841.

-Roura-Pascual, N., Suarez, A. V., Goomez, C., Pons, P., Touyama, Y., Wild, A. L. and Peterson, A.T., 2004. Geographical potential of Argentine ants (Linepithema humile Mayr) in the face of global climate change. International Journal of Biological Sciences, 271: 2527–2534.

-Scrinzi, G., Marzullo L. and Galvagni D., 2007. Development of a neural network model to update forest distribution data for managed alpine stands. Ecological Modeling, 206: 331-346.

-Stiels, D., Schidelko, K., Engler, J. O., van den Elzen, R. and Rödder, D., 2011. Predicting the potential distribution of the invasive Common Waxbill Estrilda astrild (Passeriformes: Estrildidae. Journal of Ornithology, 152: 769–780.

-Tan C. O, Özesmi U., Beklioglu, M., Per E. and Kurt B., 2006. Predictive models in ecology: Comparison of performances and assessment of applicability. Ecological Informatics, 1: 195-211.

-Thuiller, W., Lavorel, S., Araujo, M. B., Sykes, M. T., Prentice, I. C., 2005a. Climate change threats to plant diversity in Europe. Proceedings of the National Academy of Sciences, 102: 8245– 8250.

-Watts M. J., Li Y., Russell B. D., Mellin C., Connell S. D., Fordham D. A., 2011- A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks- Ecology Modelling, 222: 2606-2614.

-Willems, W., Goethals P., Eynde, D. V. D., Hoey, G. V, Lancker, V. V and Verfaillie, E., Vincx, M., Degraer, S,. 2008- Where is the worm? Predictive modelling of the habitat preferences of the tube-building polychaete Lanice conchilega. Ecological Modeling, 212: 74-79.

-Zare Chahouki, M. A., Azarnivand, H., Jafari, M. and Tavili, A., 2010. Multivariate statistical methods as a tool for model based prediction of vegetation. Russian Journal of Ecology, 41: 84-94.

-Zare Chahouki, M. A. and Khalasi Ahvazi, L., 2012. Predicting potential distributions of Zygophyllum eurypterum by three modeling techniques (ENFA, ANN and logistic) in North East of Semnan, Iran. Range Management & Agroforestry, 33(2): 123-128.

-Zare Chahouki, M. A., Khalasi Ahvazi, L. and Azarnivand, H., 2012. Predicting plant species distribution and comparison of modeling methods in Iran’s rangelands. Polish journal of ecology, 60:277-290.