برآورد رویش ده‌ساله راش (Fagus orientalis Lipsky) با استفاده از مدل شبکه‌های عصبی مصنوعی و رگرسیون خطی چندگانه در جنگل‌های رامسر

نوع مقاله : علمی - پژوهشی

نویسندگان

1 استادیار پژوهش، مؤسسه تحقیقات جنگلها و مراتع کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

2 کارشناس ارشد، موسسه تحقیقات جنگلها و مراتع کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

3 دانشجوی دکتری محیط زیست، دانشکده منابع طبیعی، دانشگاه تهران، ایران

چکیده

در این تحقیق که در جنگل‌های رامسر در استان مازندران انجام شد رویش جنگل به کمک شبکه­ عصبی مصنوعی برآورد و با رویش واقعی جنگل که به­طور مستقیم و از اندازه­گیری در 20 قطعه‌نمونه ثابت یک هکتاری که در سال­های 1381 و 1391 از آماربرداری صد­در­صد محاسبه شده بود، مقایسه شد. رویش حجمی سالانه راش به­ترتیب 52/4 و 35/4 سیلو در هکتار برای رویش به طریق مستقیم و رویش برآوردی به روش شبکه عصبی مصنوعی بود. سپس تحلیل رگرسیون، به روش گام‌به‌گام انجام و بهترین مدل­ها گزینش شد. پس از انتخاب بهترین مدل، بررسی تحلیل حساسیت ورودی­ها انجام شد. نتایج نشان داد شبکه عصبی با دقت مناسبی می­تواند رویش و مقدار برش سالیانه را برآورد کند. مقدار R2، RMSE و MAE به­ترتیب 75/0، 17 و 60/13 در شبکه ­پرسپترون چندلایه نشان داد که شبکه عصبی MLP بیشترین دقت در برآورد را دارد. در تحلیل رگرسیون خطی چندگانه هم ضرایب تشخیص به­ترتیب 610/0 و 679/0 و خطای RMS مقادیر 5/1 و 42/1 برای مدل اول و دوم به­دست آمد. نتایج مربوط به تحلیل حساسیت ورودی­ها نشان داد که عوامل حجم، جهت، قطر برابرسینه و ارتفاع درخت بیشترین تأثیر را در مدل­سازی تعیین رویش دارند. مقایسه مدل­ها نشان داد استفاده از شبکه عصبی می­تواند مقدار رویش را با دقت مناسبی پیش‌بینی کند.

کلیدواژه‌ها

عنوان مقاله [English]

Ten-year estimation of Fagus orientalis Lipsky increment using artificial neural networks model and multiple linear regression Ramsar forests

نویسندگان [English]

  • Mahmoud Bayat 1
  • Majid Hassani 2
  • Sahar Heidari 3
1 Assistant Prof., Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran
2 M.Sc. Graduate, Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran
3 PhD. Student of Environment, Faculty of Natural Resources, University of Tehran, Iran
چکیده [English]

In this research, which was done in Ramsar forests in Mazandaran province, the forest increment was estimated using artificial neural network and compared with the actual increment of the forest which was directly measured in 20 sample plots of 1 hectare in 2002 and 2012. The annual volume growth of beech was 4.52 and 4.35 m3 in hectare for direct inventory and estimation by artificial neural networks. Then regression analysis was performed to compare the results, stepwise, and the best models were selected. After selecting the best model for forecasting growth, the sensitivity analysis of inputs was investigated.The results showed that the neural network with relatively good accuracy can estimate the annual growth and cutting. The value of R2, RMSE and MAE were 0.75, 17 and 13.6 (for 20 sample plot of one hectare) respectively in the multi-layer perceptron network. Results also showed that the MLP neural network had the highest accuracy in predicting and estimation. In the analysis of multiple linear regression, the coefficients of detection were 0.610 and 0.679, respectively, and RMSE was 1.5 and 1.42, respectively, for the first and second models respectively. The volume at the beginning of the period and the diameter at breast height had the greatest impact on the amount of wood produced. Comparison of the models showed the use of neural network can predict the growth rate with proper accuracy.

کلیدواژه‌ها [English]

  • Multi Layer Perceptron
  • Sensitive analysis
  • Regression
  • Volume increment
  • Modeling

مراجع

- Amini, M., M. Namiranian, Kh. Sagheb Talebi & R. Amini, 2009. Investigation on the homogenity of diameter increment models in Fagus orientalis L. trees, Journal of Wood and Forest Science and Technology, 16(4): 1-23. (In Persian)
- Anonymos, 2001. Safarood forestry plan. Technical office of the forests, grasslands and Watershed Department, 285 p.
- Bayat, M., M. Ghorbanpour, R. Zare, A. Jaafari & B. Thai Pham, 2019b. Application of artificial neural networks for predicting tree survival and mortality in the Hyrcanian forest of Iran, Computers and Electronics in Agriculture, 164: 1-7.
- Bayat, M., M. Namiranian, M. Omid, A. Rashidi & S. Babaei, 2016. Applicability of artificial neural network for estimating the forest growing stock, Iranian Journal of Forest and Poplar Research, 24(2): 214-226. (In Persian)
- Bayat, M., A. Shekarchian & M. Omid, 2018. Predicting and assessing the tree species survival and determining Physiographic factors affecting on it in Mazandaran province Forests using artificial neural networks, Journal of Natural Environment, 70(4): 771-782.
- Bayat, M., P. Thanh Noi, R. Zare & D. Tien Bui, 2019a. A semi-empirical approach based on genetic programming for the study of biophysical controls on diameter-growth of Fagus orientalis in Northern Iran, Remote Sensing, 11(14): 1-18.
- Bayati, H. & A. Najafi, 2013. Comparison of artificial neural network üerformance with regression analysis in estimating lumber volume, Forest and wood products, 66(2): 177-191. (In Persian)
- Bednarz, Z., 2001. Dendrochronological evidence in Beech (Fagus sylvatica L.) of May late forest in the Polish Tatra national park, poster abstract 123, conference "Tree rings and people" Sep. 22-26 2001, Swiitzerland.
- Correia Vieira, G., A. Ribeiro de Mendonça, G. Fernandes da Silva, S. Sara Zanetti, M. Marques da Silva & A. Rosa dos Santos, 2017. Prognoses of diameter and height of trees of eucalyptus using artificial intelligence, Science of the Total Environmen, 619: 1473-1481
- Dittmar, C., 2001. Influence of climate on tree rings of common beech (Fagus sylvatica L.), poster abstract 7, conference "Tree rings and people" Sep 22-26 2001, Swiitzerland.
- Fakur, E., J. Alavi, M. Tabari & K. Ahmadi, 2017. Estimating the beech forest site productivity in Hyrcanian forest using classification and regression tree algorithm, Journal of Forest and Wood Productions, 70(2): 221-229. (In Persian)
- Hatami, N., M. Moayeri & H. Heidari, 2013. Volume increment determination of forest stand types in the district one of Dr Bahramnia forest management plan, Gorgan, Iranian Forests EcologyJournal, 2(3): 657-69. (In Persian)
- Jalilvand, H., Gh. Jalali, M. Akbarnia, M. Tabari & M. Hosseini, 2001. Growth response to eight hardwood species to current and past climatic variations using regression models, Journal of Agricultural. Science and Technology, 3(3): 209-225.
- Karamdost meryan, B., A. Eslam bonyad & F. Tvankar, 2019. Effect of harvest intensity on volume growth of mixed beech stands in Asalem Nav forests, Journal of Forest Research and Development, 4(4): 533-547. (In Persian)
- Köhl, M., C. Scott & A. Zingg, 1995. Evaluation of permanent sample surveys for growth and yield studies: a Swiss example, Forest Ecology and Management, 71(3): 187-194.
- Lacerda, T., C. D. Cabacinha, A. Araújo Júnior, R. Dourado Maia, K. Wesley & S. Lacerda, 2017. Artificial neural networks for estimating tree volume in the Brazilian savanna, CERNE, 23(4): 483-491.
- Ozçelik, R., J. M. Diamantopoulou, J. R. Brooks & H. V. Wiant Jr, 2010. Estimating tree bole volume using artificial neural network models for four species in Turkey, Journal of Environmental Management, 91(3): 742-753.
- Parsapazhouh, D., 1976. Investigation on the physical quality of fagus orientalis in different sites, Iranian Journal of Natural Resources, 34: 21-32. (In Persian)
- Resaneh, Y., M. H. Moshtagh Kahnamooyee & P. Salehi, 2001. Investigation of quality and qyantity of north forest, P 55-80. In: Proceedings of north forests management and stable development conference, Ramsar, Iran. (In Persian)
- Sajjadi, M., 2016. Provide vegetative models of beech species using artificial neural networks. Master's thesis. Faculty of Natural Resources. University of Tehran. Karaj, Iran. (In Persian)
- Sohrabi, H., S. M. Hosseini & M. Zobeiri, 2010. Application of Digital Surface Model for estimating forest stand volume using Regression methods and Artificial Neural Network, Iranian Journal of Natural Resources, 64(3): 223-233. (In Persian)
- Soltani, S., S. Sardari, M. Sheykhpour & S. Mousavi, 2010. Understanding the principles and applications of artificial neural networks. Scientific and Cultural Organization of Nas, Tehran, 216p. (In Persian)
- Vafaei, S., M. Pourhashemi, M. Pirbavaghar & E. Jafari, 2016. Applying artificial neural network and multiple linear regression models for estimation of forest density in Marivan forests, Iranian Journal of Forest, 7(4): 539-555. (In Persian)
- Vahedi, A., A. Mataj & R. Akhavan, 2017. Modeling the commercial volume of trees in mixed beech stands of Hyrcanian forests through artificial neural network, Forest and Wood Products, 70(1): 49-60. (In Persian)
پژوهش و توسعه جنگل
دوره 6، شماره 3
آذر 1399
صفحه 381-394

فایل ها

هم رسانی

ارجاع به این مقاله

آمار