Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Evaluating Probabilistic Deep Learning Methods for Uncertainty Quantification of Precipitation Bias Correction

Journal Article · · Artificial Intelligence for the Earth Systems
 [1];  [1];  [1];  [1];  [1];  [1]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
+ Show Author Affiliations
Climate models often exhibit biases in their precipitation predictions, particularly underestimating high-intensity events and overestimating low precipitation. Deep learning approaches offer promising solutions, but their epistemic uncertainty associated with a deep learning–based bias correction method has not previously been quantified for reliable downstream climate impact studies. While methods for capturing the epistemic uncertainty in deep learning frameworks exist, there is currently no consensus on the best method. In this work, we compare three uncertainty quantification (UQ) methods—Deep Ensembles (DEns), Monte Carlo Dropout (MCD), and Flipout—by assessing the reliability of their uncertainty estimates using standard measures such as sharpness and calibration. These UQ methods are applied to an existing deep learning precipitation bias correction model known as UFNet: a coupled U-Net and fully connected neural network. The methods utilized to assess the models’ uncertainties are 1) calibration, which ensures that the expected probabilities of the model align with reality and 2) sharpness, which is a measure of the precision of the model’s probabilistic predictions. Of the three UQ methods evaluated, the DEns and MCD methods demonstrated the best-calibrated performance (expected calibration error of 0.36 and 0.35, respectively), compared to Flipout (0.58). In contrast, Flipout had the sharpest predictions and the highest metric performance in bias correcting precipitation—especially for higher-order moments such as kurtosis with a spatial correlation of 72% compared to 32% and 55% spatial correlation for DEns and MCD, respectively. Of the three UQ methods, MCD was found to be the most suitable method for UQ purposes based on its calibration, sharpness, and computational requirements.
Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-07NA27344
Other Award/Contract Number:
22-SI-008
OSTI ID:
3018097
Report Number(s):
LLNL--JRNL-2015794
Journal Information:
Artificial Intelligence for the Earth Systems, Journal Name: Artificial Intelligence for the Earth Systems Journal Issue: 3 Vol. 4; ISSN 2769-7525
Publisher:
American Meteorological SocietyCopyright Statement
Country of Publication:
United States
Language:
English

References (1)

An investigation of perceived sharpness and sharpness metrics conference January 2005

Similar Records

Evaluating probabilistic deep learning methods for uncertainty quantification of temperature downscaling
Journal Article · Wed Dec 17 19:00:00 EST 2025 · Machine Learning: Science and Technology · OSTI ID:3014594
Uncertainty quantification of a deep learning fuel property prediction model
Journal Article · Sat Sep 23 20:00:00 EDT 2023 · Applications in Energy and Combustion Science · OSTI ID:2536669
UFNet: Joint U-Net and Fully Connected Neural Network to Bias Correct Precipitation Predictions from
Software · Tue Jul 30 20:00:00 EDT 2024 · OSTI ID:code-163562

Related Subjects

Bayesian methods
Ensembles
Geosciences
Machine learning
Precipitation
Uncertainty