Uncertainty of prediction in regression tree

How can I quantify uncertainties of predictions for new data using regression learning?

I used Regression Learner to train my data. I held out 25% of the input for validation and ran different models for training. Based on the results using RMSE and R-squared, I decided to go for regression tree and export the trained model to make predictions of new data.

Although it is possible to use the trained model to predict responses for new observations, the prediction generates a single value for each new observation and do not show uncertainties. I would like to know how it is possible to calculate the uncertainties of predictions for new data.