Latent Diffusion Model for Generating Ensembles of Climate Simulations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914859170398208 |
|---|---|
| author | Meuer, Johannes Witte, Maximilian Finn, Tobias Sebastian Timmreck, Claudia Ludwig, Thomas Kadow, Christopher |
| author_facet | Meuer, Johannes Witte, Maximilian Finn, Tobias Sebastian Timmreck, Claudia Ludwig, Thomas Kadow, Christopher |
| contents | Obtaining accurate estimates of uncertainty in climate scenarios often requires generating large ensembles of high-resolution climate simulations, a computationally expensive and memory intensive process. To address this challenge, we train a novel generative deep learning approach on extensive sets of climate simulations. The model consists of two components: a variational autoencoder for dimensionality reduction and a denoising diffusion probabilistic model that generates multiple ensemble members. We validate our model on the Max Planck Institute Grand Ensemble and show that it achieves good agreement with the original ensemble in terms of variability. By leveraging the latent space representation, our model can rapidly generate large ensembles on-the-fly with minimal memory requirements, which can significantly improve the efficiency of uncertainty quantification in climate simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02070 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Latent Diffusion Model for Generating Ensembles of Climate Simulations Meuer, Johannes Witte, Maximilian Finn, Tobias Sebastian Timmreck, Claudia Ludwig, Thomas Kadow, Christopher Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Obtaining accurate estimates of uncertainty in climate scenarios often requires generating large ensembles of high-resolution climate simulations, a computationally expensive and memory intensive process. To address this challenge, we train a novel generative deep learning approach on extensive sets of climate simulations. The model consists of two components: a variational autoencoder for dimensionality reduction and a denoising diffusion probabilistic model that generates multiple ensemble members. We validate our model on the Max Planck Institute Grand Ensemble and show that it achieves good agreement with the original ensemble in terms of variability. By leveraging the latent space representation, our model can rapidly generate large ensembles on-the-fly with minimal memory requirements, which can significantly improve the efficiency of uncertainty quantification in climate simulations. |
| title | Latent Diffusion Model for Generating Ensembles of Climate Simulations |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2407.02070 |