Dynamic conditional density network of wind vectors
Abstract
We propose the dynamic conditional density network (DCDN) to correct the bivariate normal predictive distribution commonly used to postprocess ensemble forecasts of wind vectors. The conditional distribution of the observed wind vector given the ensemble forecast may depart from the bivariate normal distribution. DCDN multiplies a bivariate normal reference density by a correction density. The correction density is a B-spline mixture on the probability integral transform scale of the reference density, and a neural network predicts its weights. DCDN equals its reference density when the correction density is uniform. We apply DCDN to ensemble forecasts of the European Centre for Medium-Range Weather Forecasts and observations at 154 sites in the Tohoku region of Japan. DCDN significantly improved the logarithmic score, energy score, and variogram score over the bivariate normal distribution predicted by a neural network. The improvement in the logarithmic score was large near zero wind speed and at higher wind speeds. This is consistent with non-normal features of the conditional distribution that the bivariate normal distribution misses.
Related
- Conditional stopping guarantees for a folded parametrization of reduced Stokes vectors
- Optimal Sobolev Rate for Gaussian Density Approximation of Wiener Chaos Vectors
- A Physically-Motivated Stochastic Model of Tropical Cyclone Dynamic Wind Fields
- SLGP: An R Package for Spatial Conditional Density Estimation
- LUCID: Local Understanding of Covariate Importance with Conditional Density Estimation
BibTeX
@misc{sato2026dynamic,
title = {{Dynamic conditional density network of wind vectors}},
author = {Keigo Sato and Yasumasa Matsuda},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35137},
eprint = {2610.35137},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35137},
}
RIS
TY - UNPB
TI - Dynamic conditional density network of wind vectors
AU - Keigo Sato
AU - Yasumasa Matsuda
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35137
UR - https://arxiv.org/abs/2610.35137
AB - We propose the dynamic conditional density network (DCDN) to correct the bivariate normal predictive distribution commonly used to postprocess ensemble forecasts of wind vectors. The conditional distribution of the observed wind vector given the ensemble forecast may depart from the bivariate normal distribution. DCDN multiplies a bivariate normal reference density by a correction density. The correction density is a B-spline mixture on the probability integral transform scale of the reference density, and a neural network predicts its weights. DCDN equals its reference density when the correction density is uniform. We apply DCDN to ensemble forecasts of the European Centre for Medium-Range Weather Forecasts and observations at 154 sites in the Tohoku region of Japan. DCDN significantly improved the logarithmic score, energy score, and variogram score over the bivariate normal distribution predicted by a neural network. The improvement in the logarithmic score was large near zero wind speed and at higher wind speeds. This is consistent with non-normal features of the conditional distribution that the bivariate normal distribution misses.
ER -