Climate change has results in increased sea surface temperatures, a northward shift in the highest intensity of typhoons, and an increase in typhoon intensity, and it is expected that future typhoon intensity changes will intensity. In this paper, a deep learning-based model for predicting typhoon intensity was developed to predict the typhoon intensity near the Korea Peninsula that can be caused by climate change scenarios. Historical environmental field data were used as training data to predict the intensity of typhoon according to changes in the future climate change environmental field using climate prediction information. As for the training data, the monthly average meteorological and oceanographic reanalysis data from June to October, which has a high frequency of typhoons from 1980 to 2022, and 241 Best Track typhoons were used as input data. A deep learning model based on Convolutional Long Short-Term Memory (ConvLSTM) was developed to predict typhoon intensity in response to environmental changes by considering both spatial and temporal features of the data. We trained the model to predict the central pressure of typhoons by learning the model with monthly averaged climate data corresponding to each movement path in the typhoon track sequence. The model using input data by setting the range to reflect the spatial characteristics of typhoons, and the best results were shown when a range of 5° × 5°. Through the sensitivity experiments using the Monte Carlo method, Sea Surface Temperature (SST) was confirmed as the variable the most influencing on model prediction.