Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions

Abstract

Soil moisture is an important variable that determines floods, vegetation health, agriculture productivity, and land surface feedbacks to the atmosphere, etc. Accurately modeling soil moisture has important implications in both weather and climate models. The recently available satellite-based observations give us a unique opportunity to build data-driven models to predict soil moisture instead of using land surface models, but previously there was no uncertainty estimate. We tested Monte Carlo dropout (MCD) with an aleatoric term for our long short-term memory models for this problem, and asked if the uncertainty terms behave as they were argued to. We show that the method successfully captures the predictive error after tuning a hyperparameter on a representative training dataset. We show the MCD uncertainty estimate, as previously argued, does detect dissimilarity.

References in corpus (9)

• Deep Learning in Neural Networks: An Overview
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales
• Deep Neural Networks as Gaussian Processes
• Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
• Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
• Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
• Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning

Cited by in corpus (4)

• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• The data synergy effects of time-series deep learning models in hydrology
• Continental-scale streamflow modeling of basins with reservoirs: towards a coherent deep-learning-based strategy
• Uncertainties of Satellite-based Essential Climate Variables from Deep Learning