:: Volume 6, Issue 12 (12-2018) ::
PEC 2018, 6(12): 153-176 Back to browse issues page
Estimation of the rangeland cover by coupling artificial neural network (ANN) and geographic information system (GIS) in Baladeh Ranglands
Abstract:   (1578 Views)

Rangeland is one of the important natural resources in different aspects such as, forage production, livestock,  promenade and soil and water conservation. Therefore, it is necessary to study rangelands for their management and conservation. Here, Field studies of rangelands are time consuming  and costly. So, it was common models application to estimate  rangelands vegetation parameters. In this study, ANN was used to estimate rangelands cover percent and GIS was used as a pre-processing and post-processing in modeling respectively in the Baladeh rangelands (Mazandaran Province). Multi-layer percepetron (MLP) network and multivariate regression method were used to estimate rangelands cover percent (training stage). In modeling process, sampling and estimation cover percent was performed  in the 127 sites. Also, the affecting factors in cover percent were evaluated such as; topography, climatic factors, soil and mankind factors. Multivariate regression and stepwise method were used to simulate rangeland cover in SPSS software. An optimal network was presented by using cover percent as desired parameter and the affecting factors in cover percent as the network inputs. Then, optimum network was verified (test stage). The study area was divided with the pixels 1×1 km (raster format) in GIS medium. Then, the model input layers were combined and a raster layer was generated that included the model inputs values and geographic coordinate. The values of pixels (model inputs) were entered into ANN with geographic coordinate. The results showed that ANN has a higher efficiency and accuracy (model test; Rsqr=0.72) than multivariate regression method (model test; Rsqr=0.6)  in rangeland cover modeling. In the next step, cover percent was simulated using the verified optimum network for all of the study rangelands. Finally, the results of ANN simulation were entered into GIS and cover percent map was generated based on the simulated results of ANN. The results showed that  coupling of ANN and GIS has an high capability (test stage: Rsr= 0.72) in rangelands cover percent modeling.

Keywords: Rangeland vegetation, Modeling, MLP, Verification, Mazandaran Province
Full-Text [PDF 422 kb]   (286 Downloads)    
Type of Study: Research | Subject: Special
Received: 2017/04/11 | Accepted: 2017/10/29 | Published: 2018/11/24
1. Aeinebeygi, S., Khaleghi, M.R., 2016. An Assessment of Biennial Enclosure Effects on Range Production, Condition and Trend (Case Study: Taftazan Rangeland, Shirvan). International Journal of Forest, Soil and Erosion (IJFSE), 6(2): 33-40.
2. Aeinebeygi, S., Khaleghi, M.R., 2016. An Assessment of Biennial Enclosure Effects on Range Production, Condition and Trend (Case Study: Taftazan Rangeland, Shirvan). International Journal of Forest, Soil and Erosion (IJFSE), 6(2): 33-40.
3. Barr T. 2002. Application of tools for hydraulic power point presentation.105-upperGotvand hydroelectric power project feasibility study.1996. Reservior Operation Flood.14p.
4. Dayhoff J. 1990. Natural Networks archictures: Anintroduction. New Yourk: Van NostrandReinhold.
5. Gangopadhyay S., Gautam T., Gupta A. 1999. Subsurface characterization using artificial neural network and GIS Journal of Computing in Civil Engineering, Co13(3):153–161.
6. Gholami V., Chau K.W., Fadaee F., Torkaman J., Ghaffari A. 2015. Modeling of groundwater level fluctuations using dendrochronology in alluvial aquifers.Journal of Hydrology,529 (2015) 1060–1069.
7. Hill M. 2001. Flood plain delineation using the HEC-GeoRAS Extention for Arcview. Brigham Young University, 514p.
8. Jafari M., Zare Chahouki M.A., Tavili A., Azarnivand H., Zahedi Amiri GH. 2004. Effective environmental factors in the distribution of vegetation types in Poshtkouh rangelands of Yazd Province (Iran). Journal of Arid Environments,Vol (56): 4, 627-641.
9. Krishna B., Styaji Rao Y.R., vijaya T. 2008. Modeling ground water levels in an urban coastal aquifer using artificial neural networks. Journal of Hydrological process, Vol.22, No.8, PP1180-1188.
10. Krishna M., Neaupane MD., MD Moqbul Hossain. 2008. Predicting Arsenic Concentration in groundwater using GIS-ANN hybrid system, 3rd IASME / WSEAS Int. Conf. on water resources, Hydraulics & Hydrolgeology (WHH '08), University of Cambridge, UK, Feb. 23-25, 2008.21.
11. Nielsen H. R. 1990. Neurocomputing. Addison-Wesley Publ. Co., Reading, MA.
12. McCoord N.M., Illingworth W.T. 1990. A practical guide to neural nets. Addison-Wesley, Publ. Co. the University of Michigan, 344p.
13. Maier H., Dandy G. 2000. Neural networks for the perdictions and forecasting of water resources variables: review of modeling issues and applications. Environmental Modelling and Software, 15,101-124.
14. Melesse A. M., Hanley R. S. 2005. Artificial neural network application for multiecosystem carbon flux simulation. Ecological Modelling, 189, 305-314.
15. Zare Chahouki M.A., KhalasiAhvazi L., Azarnivand H. 2012. Comparison of three modeling approaches for predicting plant species distribution inmountainous scrub vegetation (Semnan ranglands, Iran). Polish Journal of ecology, 60 (2): 277-289.

XML   Persian Abstract   Print

Volume 6, Issue 12 (12-2018) Back to browse issues page