A dynamic land use model, more specifically a dynamic discrete choice model, is developed in this paper to model Iowa farmers' crop choice decisions in recent years based on the newly released field-scale cropland data layers by National Agricultural Statistics Service. We explicitly consider the dynamic effects naturally arising in the corn/soybean crop system and estimate the model using the conditional choice probability method. Compared to static models, dynamic land use models perform relatively better. The dynamic models produce significantly different arc elasticity than the static model in a policy scenario when the corn price increases by 10 percent.