This paper aims to classify and predict land use/cover (LULC) for coarse spatial resolution satellite imageries of the Northern Governorate in the Kingdom of Bahrain during the period from 2016 to 2050. Satellite Images from the European Space Agency portal have been used to observe, quantify, and classify them into four classes which are water, urban area, barren land, and agricultural area. Three classifications methods namely, Maximum likelihood (ML), Random Forests (RF) and Support Vector Machine (SVM) have been conducted to classify these imageries and the results are compared based on the accuracy assessment matrices. Land change modeller (LCM) model has been used to predict the land use of the Northern Governorate based on historical transition trend and the pattern changes. This prediction model is constructed based on the Multilayer Perceptron Neural Network (MLPNN) and Markov Chain (MC) to predict the spatial dynamics of urban growth in 2030 and 2050. The prediction results show how the urban area is going to expand significantly from during (2016-2050). Also, the paper presents the future status of the agricultural area, water and barren land.