Bayesian Deep Learning for Convective Initiation Nowcasting Uncertainty Estimation
physics.ao-ph, cs.AI
Submitted: 2025-07-22
Updated: 2025-07-22
License: http://creativecommons.org/licenses/by/4.0/
The gist: This study evaluated the probability and uncertainty forecasts of five recently proposed Bayesian deep learning methods relative to a deterministic residual neural network (ResNet) baseline for 0-1 h…
Terminology
Abstract
This study evaluated the probability and uncertainty forecasts of five recently proposed Bayesian deep learning methods relative to a deterministic residual neural network (ResNet) baseline for 0-1 h convective initiation (CI) nowcasting using GOES-16 satellite infrared observations. Uncertainty was assessed by how well probabilistic forecasts were calibrated and how well uncertainty separated forecasts with large and small errors. Most of the Bayesian deep learning methods produced probabilistic forecasts that outperformed the deterministic ResNet, with one, the initial-weights ensemble + Monte Carlo (MC) dropout, an ensemble of deterministic ResNets with different initial weights to start training and dropout activated during inference, producing the most skillful and well-calibrated forecasts. The initial-weights ensemble + MC dropout benefited from generating multiple solutions that more thoroughly sampled the hypothesis space. The Bayesian ResNet ensemble was the only one that performed worse than the deterministic ResNet at longer lead times, likely due to the challenge of optimizing a larger number of parameters. To address this issue, the Bayesian-MOPED (MOdel Priors with Empirical Bayes using Deep neural network) ResNet ensemble was adopted, and it enhanced forecast skill by constraining the hypothesis search near the deterministic ResNet hypothesis. All Bayesian methods demonstrated well-calibrated uncertainty and effectively separated cases with large and small errors. In case studies, the initial-weights ensemble + MC dropout demonstrated better forecast skill than the Bayesian-MOPED ensemble and the deterministic ResNet on selected CI events in clear-sky regions. However, the initial-weights ensemble + MC dropout exhibited poorer generalization in clear-sky and anvil cloud regions without CI occurrence compared to the deterministic ResNet and Bayesian-MOPED ensemble.
Sources
- TensorFlow: A system for large-scale machine learning
- Controlled abstention neural networks for identifying skillful predictions for regression problems
- Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
- Neural networks for post-processing ensemble weather forecasts
- Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison
- Evidential Deep Learning to Quantify Classification Uncertainty
- Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
Related papers
- Anthropogenic Heat in Urban Climate Systems: Forcing, Sensitivity, and Feedback
- NORi: An ML-Augmented Ocean Boundary Layer Parameterization
- A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
- Quantifying AI data center nitrogen oxide (NO x) emissions from space
- Skillful Thunderstorm Forecasts Learned Directly from Observations
- Wind vector retrieval from miniaturized wave-enabled sea-surface drifters