Similarity estimations of satellite images of region

Abstract

Weather forecasting has abundant impacts on the society and on our daily life from cultivation to disaster measures. Previous weather forecasting models used the complicated blend of mathematical instruments which was insufficient to get a higher classification rate. In this project, we propose new novel methods for predicting monthly rainfall using machine learning algorithms. Weather forecasts are made by collecting quantitative data about the current state of the atmosphere. Machine learning algorithms can learn complex mappings from inputs to outputs, based solely on samples and require limited. Accurate prediction of weather conditions is a difficult task due to the dynamic nature of the atmosphere. To predict the future’s weather condition, the variation in the conditions in past years must be utilized. The probability that it will match within the span of an adjacent fortnight of the previous year is very high. We have proposed the use of linear regressions and Random forest algorithm for weather forecasting system with parameters such as temperature, humidity, and wind. The proposed model tends to forecast weather based on the previous record, therefore, this prediction will prove to be much reliable. The performance of the model is more accurate when compared with traditional medical analysis as it uses a fused image having higher quality.