Abstract： In order to apply the swarm intelligence (SI) algorithms effectively to solve the multimodal transportation planning problem, this paper proposed a decoding strategy to build a mapping modal between individual representation of SI and multimodal transportation schedule. In the modal, a method for traffic assignment in a multimodal transportation network was provided to decode each individual to an initial schedule. Then, a strategy for local traffic adjustment was applied to mend these initial schedules to improve the success rate of decoding. A developed particle swarm optimization (PSO) algorithm was also proposed to solve the planning problem compared with three other stateofart swarm intelligence optimization algorithms. A novel way that applies social network evolution behavior to adjust the swarm topology and individuals’ neighborhood and promote the interaction modal among individuals was introduced in the proposed algorithm. The numerical test of an operational problem shows that the decoding strategy is efficient in solving the multimodal transportation planning problem and the proposed algorithm has a superior performance on the terms of convergence speed and solution accuracy in comparison with the selected algorithms.