CLIMAGE: A New Software for the Prediction of Short-Term Weather with the Help of Satellite Data and Neuro-Fuzzy Clustering
Weather is an essential part of decision making in large-scale manufacturing, agroforestry, electrical, and various other rainfall-dependent industries. The generation and distribution of electricity, water supply, and related essential amenities of any region also depend on daily weather variations. That is why short-range weather forecasting has a direct impact on the day-to-day operations of these industries. But due to the amount of manpower, equipment, and computational capacity involved in the prediction of short-term weather, many scientists are now opting to utilize remote sensing and image processing for the estimation of next-day or 3-day weather. In short-range weather forecasting, due to the complex and nonlinear interrelationship between rainfall and weather parameters, quantification of the forecast can be error-prone. Probabilistic forecasting has proven to be more accurate. For such a level of nonlinearity as one finds in short-range forecasting, normal regression methods fail to achieve the level of accuracy required. That is why nature-based algorithms, which are well known for their ability to map the nonlinearity between dependent and independent variables, are more suitable than statistical algorithms. The present investigation tries to estimate the probability of occurrence of rainfall 1 day in advance based on the processing of satellite images and neuro-fuzzy clustering algorithms. A software module is also developed so that the model can be utilized to achieve given objectives.
KeywordsShort-range weather forecasting Neuro-fuzzy clustering Image processing
- Anton (2010) The advantages of satellite images, Retrieved from http://www.stella2000.com/the-advantages-of-satelleite-images/ on 25th Feb 2013
- Atlas R, Hoffman RN (2000) Chapter 4: The use of satellite surface wind data to improve weather analysis and forecasting at the NASA Data Assimilation Office. Elsevier Oceanogr Ser 63:57–78Google Scholar