Modeling of land use/land cover dynamics using artificial neural network and cellular automata Markov chain algorithms in Goang watershed, Ethiopia

Getahun Sisay; Berehan Gesesse; Christine Fürst; Meseret Kassie; Belaynesh Kebede

doi:10.1016/j.heliyon.2023.e20088

Modeling of land use/land cover dynamics using artificial neural network and cellular automata Markov chain algorithms in Goang watershed, Ethiopia

Heliyon. 2023 Sep 16;9(9):e20088. doi: 10.1016/j.heliyon.2023.e20088. eCollection 2023 Sep.

Authors

Getahun Sisay¹, Berehan Gesesse², Christine Fürst^{3

4}, Meseret Kassie¹, Belaynesh Kebede¹

Affiliations

¹ Department of Geography and Environmental Studies, University of Gondar, P. O. Box 196, Gondar, Ethiopia.
² Department of Remote Sensing, Entoto Observatory and Research Center, Space Science and Geospatial Institute, P.O.Box 33679, Addis Ababa, Ethiopia.
³ Department of Sustainable Landscape Development, Institute for Geosciences and Geography, Martin Luther University Halle-Wittenberg, Halle (Saale), Germany.
⁴ German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig, Puschstraße 4, 04103, Leipzig, Germany.

Abstract

Land Use/Land Cover (LULC) change has inhibited sustainable development for the last millennia by affecting climate, biological cycles, and ecosystem services and functions. In this regard, understanding the historical and future patterns of LULC change plays a crucial role in implementing effective natural resource management. This study aimed to model and characterize the spatiotemporal trajectories of landscape change between the 1984 and 2060 periods. The satellite image spectral information was segmented into seven LULC classes using a hybrid approach of image spectral recognition. The supervised classification technique of Support Vector Machine (SVM) was used to classify the satellite images, whilst the Land Change Modeler (LCM) Module in TerrSet software was used to assess the historical trend and future simulation of LULC dynamics. To predict future landscape changes, transition potential maps were generated using a Multi-layer Perceptron (MLP) neural network algorithm. The findings of the study demonstrated that the Goang Watershed has experienced significant LULC change since 1984. During the 1984-2001, 2001-2022, and 1984-2022 periods, farmland showed a dramatic increasing trend with 7.5 km²/yr^-1, 110.3 km²/yr^-1, and 64.3 km²/yr^-1, respectively. A similar trend was also observed in built-up areas with 0.5 km²/yr^-1, 3.2 km²/yr^-1, and 2 km²/yr^-1. The expansion of farmland and built-up area was at the expense of forest, shrubland, and grasslands. With a business-as-usual scenario, the extent of farmland will continue to increase between 2022 and 2060 while rapid reduction is expected by forest, shrubland, and grasslands. The alarming rate of farmland and built-up area expansion will put significant pressure on biodiversity and ecosystem services in the area. As a result, eco-friendly conservation approaches should be implemented as soon as possible to maintain ecosystem health and encourage sustainable development.

Keywords: CA-Markov; Ethiopia; Goang watershed; LULC; MLP neural network; Remote sensing.