This study proposes a model for estimating the rapid weakening of TC intensity based on deep learning using infrared satellite images and sea surface temperature (DEEP_RW_TCIE). The RW TC data are collected from two publicly available datasets: TCIR and ERA5.The RW sequential TC dataset has 1971 infrared satellite images from TCIR, which we divide into the training set, validation set, and test set according to TC examples. The 1603 satellite images before the 13th case in 2015 were divided into training sets. Moreover, the 196 satellite images from the 13th case to the 20th case in 2015 were divided into the validation set. The remaining 182 were divided into the test set.