Global warming gets some attention from the countries in the world because it is feared give negative impacts. Artificial Neural Network (NN) model can capture nonlinear relationship, so this method widely used in weather research but over-fitting may happen. Therefore to prevent overfitting of NN model, then use a Bayesian approach. Bayesian approach with Markov Chain Monte Carlo (MCMC) used to estimate parameters of NN model. The analysis best model selection based on minimum error value showed that Bayesian Neural Network model smaller than NN model for criteria training data. Based on criteria testing data, for a small lead better used Bayesian Neural Network.