Preparing of capability map for road construction using artificial neural network and GIS (case study: Arasbaran area)

Document Type : Scientific article

Authors

1 PhD student of Forest Engineering, Faculty of Natural Resources, University of Tehran, Karaj, I. R. Iran.

2 Professor, Department of Forestry and forest Economics, Faculty of Natural Resources, University of Tehran, Karaj, I. R. Iran.

3 Associate Prof., Department of Forestry and forest Economics, Faculty of Natural Resources, University of Tehran, Karaj, I. R. Iran.

4 Professor, Department of Mechanical Engineering Agricultural Machinery, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, I. R. Iran.

Abstract

The aim of the study was to provide an intelligent artificial neural networks-based method for modeling the capability of Arasbaran protected area for road crossing, in order to design, modify, and appropriate development of existing road network and communication routs in the region. First, using Analytical Hierarchy Process (AHP) and Weighted Linear Combination (WLC) method, and utilization the effective informative layers on routing, the suitability map of road construction was prepared to provide training samples in ArcGIS. In the following, Multilayer Perceptron (MLP) network was used to estimate the suitability value of road crossing. In order to evaluate the neural network’s model performance, the results were compared with the results of multivariate linear regression. According to the results, artificial neural network and statistical method of regression were shown to be useful in determining the suitability value of road crossing with coefficient of determination (R2) 0.908 and 0.901, root mean squared error (RMSE) 0.0385 and 0.04, respectively. Neural network results were relatively better than regression. Also, according to the results of sensitivity analysis of input variables, four criteria of slope, bedrock, erosion susceptibility, and soil texture showed the highest influence in estimating the model, respectively.

Keywords

References

- Abbasian, A., R. Naghdi & I. Ghajar, 2017. Planning a single low risk forest road based on artificial neural network model of landslide susceptibility (case study: Kojour watershed). Forest and Wood Products, 70(3): 499-508. (In Persian)
- Acar, H.H., E. Dursun, S. Gulci & S. Gumus, 2017. Assessment of road network planning by using GIS-based multi-criteria evaluation for conversion of coppice forest to high forest. Fresenius Environmental Bulletin, 26(3): 2380-2388.
- Alijanpour, A., J. Eshaghi Rad & A. Banej Shafiei, 2009. Comparison of woody plants diversity in protected and non-protected areas of Arasbaran forests. Iranian Journal of Forest and Poplar Research, 17(1): 125-133. (In Persian)
- Anonymous, 2016. National forest plan. Forest, Range and Watershed Organization, Tehran, 47 p. (In Persian)
- Aron, I. A., 2003. Optimal path/Neural network approaches to modeling of forest road design for use in automated GIS systems. M.Sc Thesis. University of British Colombia, Faculty of Forestry, 89 p.
- Azizi, Z. & A. Najafi, 2011. Fuzzy classification in forest area for road design (case study: Lirehsar forest, Tonekabon). Iranian Journal of Forest and Poplar Research, 19(1): 42-54. (In Persian)
- 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)
- Caliskan, E., 2013. Planning of forest road network and analysis in mountainous area. Life science journal, 10(2): 2456-2465.
- Enache, A., K. Stampfer, V. Ciobanu, O. Branzea & C. Duta, 2011. Forest road network planning with state of the art tools in a private forest district from Lower Austria. Bulletin of the Transilvania University of Brasov. Forestry, Wood Industry, Agricultural Food Engineering. Series II, 4(2): 33-40.
- Ghanbari, F., Sh. Shataee, A.A. Dehghani & Sh. Ayoubi, 2009. Tree density estimation of forests by terrain analysis and artificial neural network. Journal of Wood and Forest Science and Technology, 16(4): 25-42. (In Persian)
- Hayati, E., B. Majnounian, E. Abdi, J. Sessions & M. Makhdoum, 2013. An expert-based approach to forest road network planning by combining Delphi and spatial multi-criteria evaluation. Environmental Monitoring and Assessment, 185:1767–1776.
- Javanmard, M., E. Abdi, M. Ghatee & B. Majnounian, 2018. Forest road planning using artificial neural network and GIS. Iranian Journal of Forest, 10(2): 139-152. (In Persian)
- Khezri, S.S., A. Alijanpour, O. Hosseinzadeh & M. Erfanian, 2017. Site selection for forest park using multi-criteria decision approach in the Darreh Shohada region, Urmia. Journal of forest Research and Development, 3(2): 133-146. (In Persian)
- Kia, S.M., 2015. Neural Networks in MATLAB. Kian University Press, 408 p. (In Persian)
- Klobucar, D., R. Pernar, S. Loncaric & M. Subasic, 2008. Artificial neural networks in the assessment of stand parameter from an IKONOS satellite image. Croatian Journal of forest Engineering, 29(2): 201-211.
- Makhdoum, M., 2010. Fundamental of land use planning. Tehran University press, 289 p. (In Persian)
- Makhdoum, M., A.A. Darvishsefat, H. Jafarzadeh & A. Makhdoum, 2001. Environmental evaluation and planning by geographic information system. Tehran University press, 304 p. (In Persian)
- Mohammad-Dustar-Sharaf, M., Sh. Mirfakhraie, M.R. Zargaran & N. Azimi, 2016. Species diversity of edaphic Mesostigmatid mites (Acari: Mesostigmata) of Arasbaran Forest. Forest Research and Development, 2(1): 85-96. (In Persian)
- Mohammadi Samani, K., S.A. Hosseiny, M. Lotfalian & A. Najafi, 2010. Planning road network in mountain forests using GIS and Analytic Hierarchical Process (AHP). Caspian Journal of Environmental Science, 8(2): 151-162.
- Mostafa, M., N. Raafatnia, Sh. Shatabe & H. Ghazanfar, 2010. Forest road networks design in a multiple used forestry plan using GIS, Armardah forests of Baneh. Journal of Wood & Forest Science and Technology, 17(1):129-133. (In Persian)
- Nasr, M.S., M.A.E. Moustafa, H.A.E. Seif & G.El. Kobrosy, 2012. Application of artificial neural network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT. Alexandria Engineering Journal, 51: 37-43.
- Peng, C. & X. Wen, 1999. Recent applications of artificial neural networks in forest resource management: an overview. From: AAAI Technical Report WS-99-07, 8 p.
- Peyrov, S., A. Najafi & S.J. Alavi, 2014. Prediction of forest roadway using artificial neural network and multiple linear regressions. Journal of Forest Sustainable Development, 1(3): 285-296. (In Persian)
- Rakei, B., M. Khameh Chian, P. Abdolmaleki & P. Gyahchy, 2008. Application of artificial neural network system in landslide hazard zonation, case study: Sefidar Galle Zone in Semnan province. Journal of Tehran University Science, 33(1): 64-57. (In Persian)
- Safi, Y. & A. Bouroumi, 2013. Prediction of forest fires using artificial neural networks. Applied Mathematical Sciences, 7(6): 271 – 286.
- Salehi, A., S. Rahbari Sisakht & S. Jahangirian, 2015. Assessment of planning status of roads in Yasouj Forest Park from the natural landscapes aspects. Iranian Journal of Forest, 7(3): 377-388. (In Persian)
- Sarhangzadeh, J. & M. Makhdoum, 2002. Land use planning of Arasbaran protected region. Journal of Environmental Studies, 28(30): 31-42. (In Persian)
- Sibi, A. & N.A. Raafatnia, 2012. Consideration of effective factors in design of forest roads using Geographic Information System (GIS). Journal of Renewable Natural Resources Research, 3(1):1-12. (In Persian)
- Stefanović, B., D. Stojnić & M. Danilović, 2016. Multi-criteria forest road network planning in fire-prone environment: a case study in Serbia. Journal of Environmental Planning and Management, 59(5): 911-926.
- Sun, Y., D. Wendi, D.E. Kim & S.Y. Liong, 2015. Technical note: application of artificial neural networks in groundwater table forecasting – a case study in Singapore swamp forest. Hydrology and Earth System Sciences Discussion, 12: 9317–9336.
- Talebi, M., B. Majnounian, M. Makhdoum, E. Abdi & M. Omid, 2018. Forest road network designing for tourism development in Arasbaran protected area using GIS. RS & GIS for Natural Resources, 9(1): 93-112. (In Persian)
- Tampekis, S., S. Sakellariou, F. Samara, A. Sfougaris, D. Jaeger & O. Christopoulou, 2015. Mapping the optimal forest road network based on the multi criteria evaluation technique: the case study of Mediterranean Island of Thassos in Greece. Environmental monitoring and assessment, 187(11): 687.
- Vafakhah, M. & H. Saidian, 2015. Forecasting of runoff and sediment using neural network and multi regression in Aghajari Marls. Journal of Range and Watershed Management, 67(3): 487-499. (In Persian)
- Zabardast, L., H.R. Jafari, Z. Badehyan & M. Asheghmoala, 2011. Assessment of the trend of changes in land cover of Arasbaran protected area using satellite images of 2002, 2006 and 2008. Environmental Researches, 1(1): 23-33. (In Persian)
- Zhao, Z., T.L. Chow, H.W. Rees, Q. Yang, Z. Xing & F.R. Meng, 2009. Predict soil texture distributions using an artificial neural network model. Computers and Electronics in Agriculture, 65: 36–48.
Forest Research and Development
Volume 6, Issue 1
June 2020
Pages 121-134

Files

Share

How to cite

Statistics