Abstract: In order to solve the source identification problem of sudden water pollution accident accurately and quickly, a method based on the Differential Evolution and Markov Chain Monte Carlo (MCMC) is presented. First, the problem is considered as a Bayesian estimation problem, and the posterior probability distribution of the unknown parameters that include source’s position, intensity and events’ initial time are deduced with Bayesian inference. Second, these unknown parameters are estimated by sampling the posterior probability distribution using the Differential Evolution algorithm and Markov Chain Monte Carlo simulation, and the sources are further identified. To test the effectiveness and accuracy of the proposed method, numerical experiments are carried out, and the model result is compared to that of the Bayesian-MCMC method. The conclusions are as following: three fourth of the iterations can be reduced, the average relative error of the source’s position, intensity and events initial time are reduced 1.23%, 2.23% and 4.15%, their mean errors are decreased 0.39%,0.83% and 1.49% by using the proposed method. The latter is thus more stable and robust than the Bayesian-MCMC method, and is able to identify the sudden water pollution accidents’ source effectively. Therefore, this study provides a new approach and method to solve the difficult traceability problem of sudden water pollution accidents.