Cellular Automata models are used for simulating spatial distributions and Markov Chain models are used for simulating temporal changes. The main aim of this study is to investigate the effect of urban growth on Faisalabad. This research is aimed at predicting seasonal Land-Surface-Temperature (LST) as well as Land-Use and Land-cover (LULC) with a Cellular-Automata-Markov-Chain (CA-Markov-Chain). Landsat 5, 7 and 8 data were used for mapping seasonal LULC and LST distributions during the months of May and November for the years 1990, 1998, 2004, 2008, 2013 and 2018. A CA-Markov-Chain was developed for simulating long-term landscape changes at 10-year time steps from 2018 to 2048. Furthermore, surface temperature during summers and winters were predicted well by Urban Index (UI), a non-vegetation index, demonstrating the highest correlation of R2 = 0.8962 and R2 = 0.9212 with respect to retrieved summer and winter surface temperature. Through the CA-Markov Chain analysis, we can expect that high density and low-density residential areas will grow from 22.23 to 24.52 km2 and from 108.53 to 122.61 km2 in 2018 and 2048, as inferred from the changes occurred from 1990 to 2018. Considering UI as the predictor of seasonal LST, we predicted that the summer and winter temperature 24–28 °C and 14–16 °C and regions would decrease in coverage from 10.75 to 3.14% and from 8.81 to 3.47% between 2018 and 2048, while the summer and winter temperature 35–42 °C and winter 26–32 °C regions will increase in the proportion covered from 12.69 to 24.17% and 6.75–15.15% of city.
Multi-layer perceptron - Markov chain based geospatial analysis of land use and land cover change: A case study of Stoney Creek Watershed, BC, Canada