Due to increasing urbanization, the rapid expansion of urban spaces has become a major environmental concern over the last few decades. Therefore, modeling the urban expansion as a complex system has been scrutinized in recent years; however, determining the rules that lead to the expansion of urban areas has always been a challenging factor in this field, especially for disaggregated models like cellular automata (CA). To overcome this issue, in this research, an Adaptive Network-based Fuzzy Inference System (ANFIS) is proposed to enhance the simulation of urban growth through the automatic production of transition rules. The ANFIS can be associated with several inputs division methods, such as ANFIS accompanied by grid partitioning (ANFIS-GP), subtractive clustering (ANFIS-SC), and fuzzy c-means clustering (ANFIS-FCM). Hence, twenty-two ANFIS models based on Landsat images for the time interval from 2000 to 2010 and using different division methods were trained to investigate their effect on the efficiency of ANFIS in urban growth modeling. To examine the efficiency, the Cellular Automata-based Markov Chain (CA-MC) as a popular method was developed, and the simulation accuracy of CA-MC and the most accurate ANFIS models were obtained through comparison with observed data. The most accurate ANFIS-SC model had a Kappa of 0.76 and an overall accuracy of 93.41% for the 2019 simulated map. The results from this study reveal that the ANFIS model is effective at simulating urban expansion and the ANFIS-SC is superior to CA-MC, ANFIS-GP, and ANFIS-FCM models in urban expansion modeling.