The purpose of this study is to identify the exact location of cyclones to avert cyclone-related damage. Knowing about natural disasters like cyclones in advance will help with planning and preparations as they can be extremely dangerous. Numerous methods have been developed in the past to forecast cyclones and gauge their severity. It is a difficult task that demands swiftness and effectiveness. On the INSAT-3D dataset, a hybrid model of CNN and Bidi-rectional GRU is created in this study to estimate the position of the next cyclone. The INSAT-3D satellite pictures’ IR and visible images are analyzed and segmented using K-means clustering. The model’s training time is 400 ms, as observed. There have been comparisons between a variety of prior methods, including CNN-LSTM and a hybrid model that combines CNN and Bidirectional-LSTM. The suggested model’s experimental results show a training loss of 58.6879.