Intelligent weather forecast

In recent years, many solutions to intelligent weather forecast have been proposed, especially on temperature and rainfall, however, it is difficult to simulate the meteorological phenomena and the corresponding characters of weather when some complex differential equations and computational algorithms are merely piled up. On the basis of the review of researches on the non-linear characters of meteorology, This work describes a methodology to short-term temperature and rainfall forecasting over the east coast of China based on some necessary data preprocessing technique and the dynamic weighted time-delay neural networks (DWTDNN), in which each neuron in the input layer is scaled by a weighting function that captures the temporal dynamics of the biological task. This network is a simplified version of the focused gamma network and an extension of TDNN as it incorporates a priori knowledge available about the task into the network architecture. As an example, the estimations produced by the methodology were applied on 8 different weather forecasting data provided by the Shanghai Meteorology Centre to make the result more practical. The results confirm that proposed solutions have the potential for successful application to the problem of temperature and rainfall estimation, and the relationships between the factors that contribute to certain weather conditions can be estimated at a certain extent.