Ensemble Visualization With Variational Autoencoder
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914040025972736 |
|---|---|
| author | Wu, Cenyang Yu, Qinhan Zhou, Liang |
| author_facet | Wu, Cenyang Yu, Qinhan Zhou, Liang |
| contents | We present a new method to visualize data ensembles by constructing structured probabilistic representations in latent spaces, i.e., lower-dimensional representations of spatial data features. Our approach transforms the spatial features of an ensemble into a latent space through feature space conversion and unsupervised learning using a variational autoencoder (VAE). The resulting latent spaces follow multivariate standard Gaussian distributions, enabling analytical computation of confidence intervals and density estimation of the probabilistic distribution that generates the data ensemble. Preliminary results on a weather forecasting ensemble demonstrate the effectiveness and versatility of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13000 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ensemble Visualization With Variational Autoencoder Wu, Cenyang Yu, Qinhan Zhou, Liang Machine Learning We present a new method to visualize data ensembles by constructing structured probabilistic representations in latent spaces, i.e., lower-dimensional representations of spatial data features. Our approach transforms the spatial features of an ensemble into a latent space through feature space conversion and unsupervised learning using a variational autoencoder (VAE). The resulting latent spaces follow multivariate standard Gaussian distributions, enabling analytical computation of confidence intervals and density estimation of the probabilistic distribution that generates the data ensemble. Preliminary results on a weather forecasting ensemble demonstrate the effectiveness and versatility of our method. |
| title | Ensemble Visualization With Variational Autoencoder |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.13000 |