Weather Forecast Based on Improved Genetic Algorithm and Neural Network

Abstract

The neural network has slow convergence speed and is easy to fall into the local minimum, while the genetic algorithm is suitable for global search. The genetic algorithm late is easy near optimal solutions shocks problem and puts forward the method of fitness value of calibration, and so optimizes the purpose of the genetic algorithm. This paper will present both together. Using the improved genetic algorithm to optimize the BP neural network of weights and threshold value, and a combination of the two algorithms is applied to the weather forecast, the experiments show that the improved genetic neural network compared with the standard genetic neural network has certain advantages for improved neural network prediction ability.KeywordsGenetic algorithmNeural networkWeather forecastModel