During the past decades, Daqing City, China has experienced unprecedented urban expansion due to the rapid development of petroleum industry. With rapid urbanization and lack of strategic planning, Daqing is facing many socio-economic and environmental problems, and it is essential to examine the process of urbanization, and to develop policy recommendations for sustainable development. To address this problem, this paper examined the urbanization process of Daqing City through developing two multi-level models: an integrated system dynamic (SD) and CLUE-S model (SD-CLUES), and an integrated SD and stochastic cellular automata model (SD-CA). Analysis of results suggests that these two models generate significantly different results. With the SD-CLUES model, new urban developments are clustered in the downtown area or along major transportation networks, indicating exogenous driving forces playing an important role in shaping urban spatial dynamics. With the SD-CA model, on the contrary, the resultant new urban cells are spread over the entire study area, and associated with existing urban areas. Further, visual comparisons and validations indicate that the SD-CA model is a better alternative in explaining the urbanization mechanism of Daqing City. In addition, analysis of results suggests that the stochastic factor in the CA model has significant impact on the modeling accuracy.
