Coupling of Markov chains and cellular automata spatial models to predict land cover changes (case study: upper Ci Leungsi catchment area)

2nd International Conference of Indonesian Society for Remote Sensing 2016

地球科学;计算机科学

Marko, K.^1 ; Zulkarnain, F.^1 ; Kusratmoko, E.^1

Department of Geography, Faculty of Mathematics and Natural Science, Universitas Indonesia, Kampus UI Depok, Depok

16424, Indonesia^1

关键词: Kappa coefficient;    Land-cover change;    Metropolitan area;    Multi Criteria Analysis;    Prediction model;    Remote sensing satellites;    Spatial patterns;    Urban heat island;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/47/1/012032/pdf
DOI  :  10.1088/1755-1315/47/1/012032

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Land cover changes particular in urban catchment area has been rapidly occur. Land cover changes occur as a result of increasing demand for built-up area. Various kinds of environmental and hydrological problems e.g. floods and urban heat island can happen if the changes are uncontrolled. This study aims to predict land cover changes using coupling of Markov chains and cellular automata. One of the most rapid land cover changes is occurs at upper Ci Leungsi catchment area that located near Bekasi City and Jakarta Metropolitan Area. Markov chains has a good ability to predict the probability of change statistically while cellular automata believed as a powerful method in reading the spatial patterns of change. Temporal land cover data was obtained by remote sensing satellite imageries. In addition, this study also used multi-criteria analysis to determine which driving factor that could stimulate the changes such as proximity, elevation, and slope. Coupling of these two methods could give better prediction model rather than just using it separately. The prediction model was validated using existing 2015 land cover data and shown a satisfactory kappa coefficient. The most significant increasing land cover is built-up area from 24% to 53%.