The invention provides a mid-and-long term runoff forecasting method based on a bacteria foraging optimization algorithm, and belongs to the technical field of hydrologic forecasting. In the method, firstly a circulation index which has a large correlation coefficient and has physical influence on the runoff of a drainage basin to be forecasted is taken as a forecast factor, and the forecast factor value is subjected to normalization processing; then the historical samples of the drainage basin to be forecasted are selected and are divided into a training set and a testing set; a support vector regression machine (SVR) model is trained by means of the training set, the parameter value of the model is determined by means of the bacteria foraging optimization algorithm, and the bacteria with the maximum adaptability value is output; the bacteria is decoded, and the optimum value and the preliminary forecasting result of the SVR model parameter are obtained; the preliminary forecasting result is compared with the testing set, and the error is analyzed, if the error is within a set scope, the final forecasting result is outputted. According to the invention, the forecasting accuracy, the generalization ability and the practicality of the mid-and-long term runoff forecasting method employing the SVR model are improved, and the mid-and-long term runoff forecasting method can serve as an effective method for mid-and-long term runoff forecasting.