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.
@article{arxiv.2109.07250,
title = {Adding Uncertainty to Neural Network Regression Tasks in the Geosciences},
author = {Elizabeth A. Barnes and Randal J. Barnes and Nicolas Gordillo},
journal= {arXiv preprint arXiv:2109.07250},
year = {2021}
}