Accurate prediction of precipitation is of great importance for irrigation management and disaster prevention. In this study, back propagation artificial neural network (BPANN), radial basis function artificial neural network (RBFANN) and Kriging methods were applied and compared to predict the monthly precipitation of Liaoyuan city, China. Autocorrelation analysis method was used to determine model input variables first, and then BPANN, RBFANN and Kriging methods were applied to recognize the relationship between previous precipitation and later precipitation with the monthly precipitation data of 1971–2009 in Liaoyuan city. At last, the three models performance were compared based on models accuracy, models stability and models computational cost. Comparison results showed that for model accuracy, RBFANN performed best, the followed is Kriging, BPANN preformed worst; for stability and computational cost, RBFANN and Kriging models perform better than BPANN model. In conclusion, RBFANN is the best method for precipitation prediction in Liaoyuan city. Therefore, the developed RBFANN model was applied to predict the monthly precipitation of 2010–2019 in the study area.
- monthly precipitation
- Liaoyuan city
- artificial neural network
- First received 2 November 2015.
- Accepted in revised form 11 January 2016.
- © IWA Publishing 2016