Research And Application Of Flood Forecasting Of Neural Network Based On Genetic Algorithm

Flood forecasting, which is a complex system with strong nonlinear feature, is a very crucial non-structural measure of flood mitigation to adapt nature and mitigate losses, and directly serves for flood defense, reasonable utilization and protection of water resources, construction, operation and management of hydraulic structure and developments of industry and agriculture. Nowadays, whether deterministic hydrologic model or stochastic hydrologic model is founded upon observed data. Due to the restriction of assumptions in model-construction, these models, in a great sense, are a kind of analogy of actual hydrologic laws, and are hard to deal with complex nonlinear relations among hydrologic phenomena and their factors. Based on a summary of domestic and abroad study, this paper tries to establish GA-LMBP neural network flood forecasting model, which combines Artificial Neural Network (ANN) and Genetic Algorithms (GA). The framework and research are listed as follows:1. The paper clarifies the basic principle and the study process of BP neural network, analyses the existing weakness and introduces some general improvement measure.2. Aiming at the complex relations of hydrologic phenomena and their factors, making use of excellent global searching ability of GA and fine learning ability of ANN. Using GA to optimize initial weights of neural network to design GA_LMBP algorithm, in a sense, local optimizing problems, which is widely existed in neural network model training, can be overcome.3. Taken a reservoir historical runoff data as examples, testifying the GA_LMBP algorithm, applying MATLAB software to simulation and comparingwith the simulation of general BP improvement method. Result indicates this algorithm has a better stability, precision and robustness than the traditional BP neural network. It is the reliable and accurate methods in flood forecasting.