Abstract. This paper studies on the prediction of the hail. First, Cellular Neural Network method acts on the cloud radar images to extract their edge, The cloud's contour feature would be more clear; and then, the edge detection would be processed by wavelet transform. Five different coefficients would be found; At last we construct hail cloud life feature vector matrix, explain the problem by matrix form, so as to find the corresponding rules through the five coefficients, after seeking to rules, through the simulation experiment, to achieve the purpose of hail forecast.

Road quality information detect system is an important component in architecture quality detect system, also is the basement of successfully working of other related project for the whole country. The study of detecting the road crack is the key to insure the security of accurately detect the road quality in transportation system. In this paper, we come up with a fixed way of road undersized rift image detection by using cellular neural networks. By image processing, building rift networks and details networks and adding the model of similarity undersized rift networks. It can avoid the problem that can not accurately detect undersized crack by only taking the crack feature value. The experiment proved that fixed crack detect computing is easy to do, more accurate to detect the undersized cracks on the road and can reach the standard level of current detect technique.