Automatic Detection of Chaos Phenomenon in Tornadoes Prediction Using Edge Detection

Cumulonimbus clouds is one of the early formations that leads to a small scale tornado known locally in Indonesia as waterspout. The clouds cumulonimbus shows some irregular and undefined phenomena called chaos. However, in order to make sure that a chaos phenomenon will lead to the occurance of tornadoes, some criteria and characteristics should be fulfilled. One of such criteria is an extreme heat that is caused by the formation of clouds cumulonimbus. On the gray color edge of the cumulonimbus clouds there are some conditions that characterize the image such as wavelength, frequency and the intensity of the colors in clouds cumulonimbus images, as well as the different levels of the brightness and darkness. In addition, color of the image could be used also as a basis to define the parameters related to the start condition of the tornado. In this research, edge detection algorithm is used to get the gray edge boundary, with mean to extract the intensification of irregular patterns on cumulonimbus clouds in order to automatically predict the occurrence of tornadoes. The results of this research show that the edge detection approach is a promising technique for prediction of tornado occurrence.