Applicability of artificial neural network for estimating the forest growing stock | ||
| تحقیقات جنگل و صنوبر ایران | ||
| Article 4, Volume 24, Issue 2 - Serial Number 64, June 2016, Pages 226-214 PDF (1.3 M) | ||
| Document Type: Research article | ||
| DOI: 10.22092/ijfpr.2016.106985 | ||
| Authors | ||
| Mahmoud Bayat* ; Manouchehr Namiranian; Mahmoud Omid; Arman Rashidi; Sajjad Babaei | ||
| Abstract | ||
| Knowledge on stand’s quantitative and qualitative characteristics (tree volume and growth) are fundamental requirements for monitoring close-to-nature forest management plans. In addition, future planning is based on statistics and information obtained from the forest. Thus, structural information such as standing stock, growth and diameter distribution are highly required. Volume increment provides the amount of allowable annual cut. In this study 768.4 ha of virgin forests located in Gorazbon district in Kheyroud educational- experimental Forest was inventoried by 258 permanent sample plots measured in 2012. Following elimination of statistical deficiency and exclusion of deviated points, the data were divided into 80% training and 20% test data to examine the applied neural network. The data was initially standardized by using training data. Neural network with back propagation error algorithm was developed. Furthermore, volume was regressed against diameter, height, slope and aspect using the allocated training data. Model diagnostics including R2, MAE and RMSE were applied for evaluating those two methods. The analysis resulted in R2=0.98, MAE=0.69 and RMSE=1.006, respectively. For the regression method the diagnostics amounted in R2=0.85, MAE=0.95 and RMSE=2.5. The results have suggest the higher accuracy of neural network for growing stock estimation compared to regression approach. However, care must be taken during data preparation, network design and network training to reach an optimum final model. It is concluded that this model should be further considered and applied for the estimation of volume across the study area. | ||
| Keywords | ||
| Gorazbon section; Artificial Neural Network; regressions models; volume | ||
| References | ||
|
- Bayat, M., Namiranian, M., Zobeiri, M. and Fathi, J., 2013a. Determining the growing volume and number of trees in the forest using permanent sample plots. Iranian Journal of Forest and Poplar Research, 21(3): 424-438 (In Persian). - Bayat, M., Pukkala, T., Namiranian, M. and Zobeiri, M., 2013b. Productivity and optimal management of the uneven-aged hardwood forests of Hyrcania. European Journal of Forest Research, 132(5-6): 851-864. - Bayat, M., Namiranian, M. and Zobeiri, M., 2014. Volume, height and wood production modeling using the changes in a nine years rotation (case study: Gorazbon district in Kheyroud forest, north of Iran). Journal of Forest and Wood Products, 67(3): 423-435 (In Persian). - Bayat, M., Namiranian, M. and Zobeiri, M. and Pukkala, T., 2015. Growth models using to simulate and investigate different forest management methods (Case study: Gorazbon district in Kheyroud forest, north of Iran). Journal of Forest and Wood Products, 67(4): 595-612 (In Persian). - Benediktsson, J.A., Swain, P.H. and Erosy, O.K., 1990. Neural network approaches versus statistical methods in classification of multisource remote sensing data. IEEE Transaction on Geosciences and Remote Sensing, 28(4): 540-552. - Blackard, J.A. and Dean, D.J., 1999. Comparative accuracies of artificial neural networksand discriminant analysis in predicting forest cover types from cartographic variables. Computersand Electronics in Agriculture, 24(3): 231-251. - Bourque, Ch. and Bayat, M., 2015. Landscape variation in tree species richness in northern Iran forests. PLOS One, 10(4):1-17 - Diamantopoulou, M.J., 2005. Artificial neural networks as an alternative tool in pine bark volume estimation. Computers and Electronics in Agriculture, 48: 235-244. - Etemad, V., 2002. Quantity and quality investigation seed of fagus in forests of Mazandaran province. Ph.D. thesis, Faculty of Natural Resources, University of Tehran, Karaj, 258p (In Persian). - Farshad Far, A., 2002. Regression Analysis. University of Tehran Press, Tehran, 771p (In Persian). - Ghanbari, F., Shataee, Sh., Dehghani, A.A. and Ayoubi, Sh., 2009. Tree density estimation of forests by terrain analysis and artificial neural network. Journal of Wood & Forest Science and Technology, 16(4): 25-42 (In Persian). - Gimblett, R.H. and Ball, G.L., 1995. Neural network architectures for monitoring and simulating changes in forest resources management. AI Applications, 9(2): 103-123. - Hanewinkela, M., Zhou, W. and Schill, Ch., 2004. A neural network approach to identify forest stands susceptible to wind damage. Forest Ecology and Management, 196(2): 227-243. - Hasenauer, H., Merkl, D. and Weingartner, M., 2001. Estimating tree mortality of Norway spruce stands with neural networks. Advances in Environmental Research, 5: 405-414. - Hokka, H., 1999. Forest modeling and management. Silva Fennica, 34: 251-272. - Jahani, A., Feghhi, J., Makhdoum, M. and Omid, M., 2016. Optimized forest degradation model (OFDM): an environmental decision support system for environmental impact assessment using an artificial neural network. Journal of Environmental Planning and Management, 59(2): 222-244. - Jalilvand, H., 2003. Model and simulation growth reaction in tree of forest to climate and nourishment variables. Ph.D. thesis, Faculty of Natural Resources, University of Tarbiat Modares, Noor, 258p (In Persian). - Karaman, A. and Caliskan, E., 2009. Affective factors weight estimation in tree felling time by artificial neural networks. Expert Systems with Applications, 36: 4491-4496. - Marvie-Mohadjer, M., Zobeiri, M., Etemad, V. and Jourgholami., M., 2009. Performing of the single selection method at compartment level and necessity for full inventory of tree species (Case study: Gorazbon district in Kheyroud forest, north of Iran). Iranian Journal of Natural Resources, 61(4): 889-908 (In Persian). - Naghdi, R. and Ghajar, I., 2012. Application of artificial neural network in the modeling of skidding time prediction. Advanced Materials Research, 403: 3538-3543 (In Persian). - Namiranian, M., 2010. Tree Measurement and Forest Bioinventory. University of Tehran Press, Tehran, 574p (In Persian). - Pukkala, T., 2009. Growth and yield models for uneven aged stand in Finland. Forest Ecology and Management, 258: 207-216. - Zobeiri, M., 2008. Forest Biometry. University of Tehran Press, Tehran, 407p (In Persian). - Zobeiri, M., 2011. Forest Inventory (Tree Measurement). University of Tehran Press, Tehran, 401p (In Persian). | ||
|
Statistics Article View: 1,546 PDF Download: 1,167 |
||
Journal management system. designed by sinaweb