Probabilistic adjustment of seasonal forecasts using cVAE with a non-parametric decoder: A case study of Arctic sea ice predictions
Abstract
Seasonal climate predictions support planning and risk management by offering early information of the likely climate conditions in the coming months, and associated uncertainties. Ensemble forecasts enable this by simulating many plausible outcomes, allowing predictions to be expressed as usable probabilities. Large ensembles and high-resolution forecasts strengthen this by better sampling uncertainty and capturing finer-scale processes but come with significant computational cost. Moreover, forecast ensembles drift and exhibit systematic biases and spatio-temporal errors that grow with lead time, requiring careful post-processing and calibration. A probabilistic post-processing framework based on conditional Variational Autoencoders (cVAEs) was developed at the Canadian Center for Climate Modeling and Analysis to generate large ensembles of adjusted seasonal predictions of Arctic sea ice. The generative model was designed to learn the observational distribution conditioned on the biased model prediction. This enables generation of arbitrarily large ensembles of calibrated, bias corrected forecasts with improved skill. Here, we extend this framework to a Generalized Variational Inference problem to address the loss of fine-scale energy and the characteristic blurriness, a known limitation of standard cVAEs. Specifically, we employ a generator in place of the Gaussian parametrized decoder in cVAE and use Continuous Ranked Probability Score (CRPS) in the objective function instead of the Gaussian log-likelihood. We further use a higher resolution target dataset compared to the raw forecast. We show that the adjusted forecasts are better calibrated, more consistent with the observational distribution, and exhibit smaller errors than benchmark predictions, while also enhancing the resolution of the raw forecasts and improving sharpness and spectral power relative to the standard cVAE.
Related
- Probabilistic Streamflow Forecasts for Mississippi River Navigation Risk and Parametric Insurance
- Learning joint probabilistic weather forecasts from station observations alone
- Six-hourly Probabilistic Precipitation Forecasts Created From Hourly Probabilities
- Evaluating Neural Probabilistic Forecasts of Sparse Earthquake Counts: What Survives a Careful Evaluation
- The need for uncertainty: why probabilistic LSTMs are key to improving flood predictions and enabling learned warning rules
BibTeX
@misc{gooya2026probabilistic,
title = {{Probabilistic adjustment of seasonal forecasts using cVAE with a non-parametric decoder: A case study of Arctic sea ice predictions}},
author = {Parsa Gooya and Reinel Sospedra-Alfonso},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.29172},
eprint = {2605.29172},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.29172},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Probabilistic adjustment of seasonal forecasts using cVAE with a non-parametric decoder: A case study of Arctic sea ice predictions
AU - Parsa Gooya
AU - Reinel Sospedra-Alfonso
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2605.29172
UR - https://arxiv.org/abs/2605.29172
AB - Seasonal climate predictions support planning and risk management by offering early information of the likely climate conditions in the coming months, and associated uncertainties. Ensemble forecasts enable this by simulating many plausible outcomes, allowing predictions to be expressed as usable probabilities. Large ensembles and high-resolution forecasts strengthen this by better sampling uncertainty and capturing finer-scale processes but come with significant computational cost. Moreover, forecast ensembles drift and exhibit systematic biases and spatio-temporal errors that grow with lead time, requiring careful post-processing and calibration. A probabilistic post-processing framework based on conditional Variational Autoencoders (cVAEs) was developed at the Canadian Center for Climate Modeling and Analysis to generate large ensembles of adjusted seasonal predictions of Arctic sea ice. The generative model was designed to learn the observational distribution conditioned on the biased model prediction. This enables generation of arbitrarily large ensembles of calibrated, bias corrected forecasts with improved skill. Here, we extend this framework to a Generalized Variational Inference problem to address the loss of fine-scale energy and the characteristic blurriness, a known limitation of standard cVAEs. Specifically, we employ a generator in place of the Gaussian parametrized decoder in cVAE and use Continuous Ranked Probability Score (CRPS) in the objective function instead of the Gaussian log-likelihood. We further use a higher resolution target dataset compared to the raw forecast. We show that the adjusted forecasts are better calibrated, more consistent with the observational distribution, and exhibit smaller errors than benchmark predictions, while also enhancing the resolution of the raw forecasts and improving sharpness and spectral power relative to the standard cVAE.
ER -