Adding Uncertainty to Neural Network Regression Tasks in the Geosciences
Elizabeth A. Barnes, Randal J. Barnes, Nicolas Gordillo · arXiv (Cornell University) · 2021
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.