UDC 528.7
UDC 528.8
CSCSTI 89.57
Artificial Neural Network (ANN) are advanced pattern recognition algorithms capable of extracting complex nonlinear relationships between variables. This paper presents the application of artificial neural networks, in particular the Multi-layer Perceptrons (MLP) neural networks from the Land Change Modeler (LCM) to model the potential for land use change under the influence of natural factors. A case study conducted in Giao Thuy district is used to illustrate this method. Land use data from 2001 to 2013 were decoded using Landsat satellite images. The data analysis process was carried out using TerrSet software to obtain a simple MLP neural network consisting of an input layer (3 neurons), a hidden layer (7 neurons), and an output layer (2 neurons). The results of the study show that the MLP network works with high reliability. The overall (with all variables) efficiency of 0.6858 and accuracy of 84.29 % of the model are well above the acceptable limit to be used for training. The results of the study show that the three factors influencing land use change can be ranked in order: soils, geomorphology and finally the distance to the coastline have the greatest influence.
land use change, multilayer perceptrons, artificial neural networks, Cramer’s V, backpropagation algorithm, natural factors
1. Kuemmerle T, Chaskovskyy O, Knorn J, et al. Forest cover change and illegal logging in the Ukrainian Carpathians in the transition period from 1988 to 2007. Remote Sensing of Environment. 2009;113(6): 1194–1207. DOIhttps://doi.org/10.1016/j.rse.2009.02.006.
2. Mas JF, Kolb M, Paegelow M, et al. Inductive pattern-based land use/cover change models: A comparison of four software packages. Environmental Modelling & Software. 2014;51: 94–111. DOIhttps://doi.org/10.1016/j.envsoft.2013.09.010.
3. Amiraslani F, Dragovich D. Combating desertification in Iran over the last 50 years: An overview of changing approaches. Journal of Environmental Management. 2011;92(1): 1–13. DOIhttps://doi.org/10.1016/j.jenvman.2010.08.012.
4. Maithani S. A Neural Network based Urban Growth Model of an Indian City. Journal of the Indian Society of Remote Sensing. 2010;37(3): 363–376. DOIhttps://doi.org/10.1007/s12524-009-0041-7.
5. Pérez Vega A, Mas JF, Ligmann-Zielinska A. Comparing two approaches to land use/cover change modeling and their implications for the assessment of biodiversity loss in a deciduous tropical forest. Environmental Modelling & Software. 2012;29(1): 11–23. DOIhttps://doi.org/10.1016/j.envsoft.2011.09.011.
6. Fathizad H, Hakimzadeh Ardakani MA, Taghizadeh Mehrjardi RA, et al. Modeling Land Use Change Process by Integrating the MLP Neural Network Model in the Central Desert Regions of Iran. Desert. 2019;24(2): 241–254. DOIhttps://doi.org/10.22059/jdesert.2019.76364.
7. Shafizadeh-Moghadam H, Tayyebi A, Helbich M. Transition index maps for urban growth simulation: application of artificial neural networks, weight of evidence and fuzzy multi-criteria evaluation. Environmental Monitoring and Assessment. 2017;189(6): 189–300. DOIhttps://doi.org/10.1007/s10661-017-5986-3.
8. Nguyen VN, Nguyen CC. Application of multilayer artificial neural network in establishing a flash flood zoning model in the Northwestern mountainous region, experimentally in Yen Bai Province. Journal of Mine Surveying and Cartographic Science. 2020;44: 56–64. (In Vietnamese). DOIhttps://doi.org/10.54491/jgac.2020.44.304.
9. Azari M, Tayyebi A, Helbich M, et al. Integrating Cellular Automata, Artificial Neural Network and Fuzzy Set Theory to Simulate Threatened Orchards: Application to Maragheh, Iran. GIScience & Remote Sensing. 2016;53(2): 183–205. DOIhttps://doi.org/10.1080/15481603.2015.1137111.
10. Girma R, Fürst Ch, Moges A. Land Use Land Cover Change Modeling by Integrating Artificial-Neural-Network with Cellular Automata-Markov Chain Model in Gidabo River Basin, Main Ethiopian Rift. Environmental Challenges. 2021;6(10): 100419. DOIhttps://doi.org/10.1016/j.envc.2021.100419.
11. Gharaibeh A, Shaamala A, Obeidat R, et al. Improving land-use change modeling by integrating ANN with Cellular Automata-Markov Chain model. Heliyon. 2020;6(9):1–18. DOIhttps://doi.org/10.1016/j.heliyon.2020.e05092.
