Abstract: Abstract: Crop pattern is a key element in agricultural land systems other than land use and land cover. Crop pattern dynamic changes take place very frequently, but they are not always easily observable, making many difficulties for analysis. As an effective tool for understanding the driver, process and consequence of agricultural land system changes, the spatially-explicit agent-based land change models have successfully been applied in representing human and natural interactions on agricultural landscapes. With the assumption that the crop pattern at a regional level is the aggregation of crop choices at the filed level, we conceptualized an agent-based model to simulate crop pattern dynamics at a regional scale (CroPaDy), which was supposed to represent the frequent but uneasily observed crop pattern changes in agricultural land systems. The conceptualization of CroPaDy model was designed strictly following the standard protocol for agent-based modeling. However, the computational model hinders its application because it needs a grid-based representation and the model itself is complicated with multi objectives, and nested by 3 interactive sub modules. As CroPaDy model can hardly been developed by the common agent-based modeling platforms, such as RePast, NetLogo, and Swarm, we are trying to use another alternative MATLAB to realize an empirical based application in an agricultural region of Northeast China, by taking the advantage of powerful and open-accessed matrix computing ability of MATLAB. We coded the model for the 3 interactive sub modules in steps: 1) Agents generating module. The Monte Carlo method was used to generate the internal factors (family attributes) for each individual agent in the full coverage study region by combining GIS data, statistical data, survey data and the individual based blanket rules. 2) Agent classifying module. The back propagation artificial neural network method was used to automatically classify the generated agents to groups based on the performance of surveyed agents, and the different groups were further linked with discrete probability on making a certain decision. 3) A probabilistic approach was used to determine the decisions of agent in each modeling period. The survey based data was used to support the empirical based application. After coding CroPaDy model in MATLAB with an input of 114 m×114 m grid-based ASCII file (total grid number = 29 799) plus 384 surveyed households randomly distributed on the selected grids, the model can successfully run and output model results for visualization and analysis. The results suggest that the crop areas of maize, rice, soybean, and tobacco are 26 055.9, 3 506.8, 5 192.2, 3 983.9 hm2 respectively. Comparing with the local statistic yearbook, the overall accuracy of CroPaDy model can reach as high as 90%. Therefore, it is concluded that not only the conceptual framework of CroPaDy model is able to present the interactions between human and environment in agricultural land systems, but also the computational model can be finely programmed with MATLAB software. The study can further prove that crop pattern dynamics can be modeled by capturing farmer's land use decisions, and CroPaDy model can be applied in other similar regions if the detailed household survey data is available.