River runoff forecasting is necessary for numerous applications related to water use, including water supply management, power generation and flooding protection measures. In this study, a regional model using an artificial neural network (ANN) is proposed for monthly runoff forecasting, which considers stations linked to the network that belong to the same homogeneous region, and are delimited using K-means (KM-ANN) and L-moments (LM-ANN) techniques. This methodology was applied to a sample of 90 monthly runoff series in southern Canada. The results were compared to those of a traditional neural network for a given site (ANNs) using statistical indices, such as root-mean-squared error (RMSE), relative square error (RSE), mean absolute error (MAE), relative absolute error (RAE), the concordance index (d) and the coefficient of determination (r2). The LM-ANN technique produced better forecasts in 56.7% of the analysed stations, whereas the KM-ANN and ANN techniques produced better forecasts in 27.7% and 15.6% of the stations, respectively. Thus, the results indicate that the regionalisation process improved the forecasts in 84.4% of the studied cases, and the estimation uncertainty was reduced by an average of 31.8%, according to the RMSE, RSE, MAE and RAE values. Therefore, its application is recommended in Canada, where it would be useful for the Integrated Water Resources Management Program.