Using conventional statistical models, AACPDC has trouble accurately predicting land use patterns in the city. These models frequently have trouble considering the intricate dynamics and spatial interactions that affect how land is used. Because of this, the AACPDC needs a sophisticated strategy that combines Markov chain, cellular automata techniques in order to increase the precision and dependability of land usage predictions. The challenge is in creating and putting into practice a comprehensive model that successfully considers pertinent data, spatial heterogeneity, and adheres to the urban planning framework of the AACPDC. The study's goals are to create an integrated model for predicting changes in land use, incorporate relevant data specific to Addis Ababa's city administration (Arada, Kirkos, Lideta, and a combination of the three), forecast future land use changes, support evidence-based urban planning decisions, and help with resource allocation. The methodology includes gathering and preprocessing data, categorizing different types of land use, performing a Markov Chain analysis, creating a cellular automata model, and validating the model. Quantum Geographic Information Systems and Geographic Information Systems were used as the research's tools to forecast changes in land use from one state to another as well as to establish land use classes and train the ANN and LR respectively. The Addis Ababa City Plan and Development Commission and the Addis Ababa City Land Holding Registration and Information Agency were the study's primary data sources. The data was gathered through interview, observation, and document review. The prediction of the change in land use for the year 2031 was made using this simulation. By facilitating proactive planning and policy formulation, enabling informed decision-making in urban planning, and supporting the objectives of the Addis Ababa City Development Plan, the study's findings will contribute to the sustainable development of the Addis Ababa City Administration. The study supports the incorporate predictive models (Markov Chain and Cellular Automata), improving data availability and quality, Regular updates and maintenance, collaborations with research institutions and stakeholders, establishing a framework for regular monitoring and evaluation. Key words: Land use, Markov Chain, Cellular Automata, Geographical Information System, Quantum Geographical Information System