Adding Uncertainty to Neural Network Regression Tasks in the Geosciences

A simple method for adding uncertainty to neural network regression tasks via estimation of a general probability distribution is described. The methodology supports estimation of heteroscedastic, asymmetric uncertainties by a simple modification of the network output and loss function. Method performance is demonstrated with a simple one dimensional data set and then applied to a more complex regression task using synthetic climate data. ∗Corresponding author webpage: http://barnes.atmos.colostate.edu ar X iv :2 10 9. 07 25 0v 1 [ ph ys ic s. ao -p h] 1 5 Se p 20 21 ADDING UNCERTAINTY TO NEURAL NETWORK REGRESSION TASKS