Latent Diffusion Model for Generating Ensembles of Climate Simulations
- URL: http://arxiv.org/abs/2407.02070v2
- Date: Thu, 4 Jul 2024 12:43:52 GMT
- Title: Latent Diffusion Model for Generating Ensembles of Climate Simulations
- Authors: Johannes Meuer, Maximilian Witte, Tobias Sebastian Finn, Claudia Timmreck, Thomas Ludwig, Christopher Kadow,
- Abstract summary: We train a novel generative deep learning approach on extensive sets of climate simulations.
By leveraging the latent space representation, our model can rapidly generate large ensembles on-the-fly with minimal memory requirements.
- Score: 2.144088660722956
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: 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.
Related papers
- Probabilistic Emulation of a Global Climate Model with Spherical DYffusion [15.460280166612119]
We present the first conditional generative model able to produce global climate ensemble simulations that are accurate and physically consistent.
Our approach beats relevant baselines and nearly reaches a gold standard for successful climate model emulation.
arXiv Detail & Related papers (2024-06-21T00:16:55Z) - Embedding machine-learnt sub-grid variability improves climate model biases [0.44998333629984877]
Under-representation of cloud formation is a long-standing bias associated with climate simulations.
We overcome these biases by embedding a Multi-Output Gaussian Process (MOGP) trained on high resolution Unified Model simulations.
Ten-year predictions are generated for both control and ML-hybrid models.
arXiv Detail & Related papers (2024-06-13T19:35:58Z) - SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
Weather forecasting plays a critical role in various sectors, driving decision-making and risk management.
Traditional methods often struggle to capture the complex dynamics of meteorological systems.
We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
arXiv Detail & Related papers (2024-05-29T08:00:15Z) - Combining deep generative models with extreme value theory for synthetic
hazard simulation: a multivariate and spatially coherent approach [0.0]
Generative adversarial networks (GANs) are well-suited to such a problem due to their ability to implicitly learn the distribution of data in high-dimensional settings.
We employ a GAN to model the dependence structure for daily maximum wind speed, significant wave height, and total precipitation over the Bay of Bengal.
Once trained, the model can be used to efficiently generate thousands of realistic compound hazard events.
arXiv Detail & Related papers (2023-11-30T12:55:51Z) - Real-time high-resolution CO$_2$ geological storage prediction using
nested Fourier neural operators [58.728312684306545]
Carbon capture and storage (CCS) plays an essential role in global decarbonization.
Scaling up CCS deployment requires accurate and high-resolution modeling of the storage reservoir pressure buildup and the gaseous plume migration.
We introduce Nested Fourier Neural Operator (FNO), a machine-learning framework for high-resolution dynamic 3D CO2 storage modeling at a basin scale.
arXiv Detail & Related papers (2022-10-31T04:04:03Z) - Multi-fidelity Hierarchical Neural Processes [79.0284780825048]
Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs.
We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling.
We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation.
arXiv Detail & Related papers (2022-06-10T04:54:13Z) - Closed-form Continuous-Depth Models [99.40335716948101]
Continuous-depth neural models rely on advanced numerical differential equation solvers.
We present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster.
arXiv Detail & Related papers (2021-06-25T22:08:51Z) - DeepClimGAN: A High-Resolution Climate Data Generator [60.59639064716545]
Earth system models (ESMs) are often used to generate future projections of climate change scenarios.
As a compromise, emulators are substantially less expensive but may not have all of the complexity of an ESM.
Here we demonstrate the use of a conditional generative adversarial network (GAN) to act as an ESM emulator.
arXiv Detail & Related papers (2020-11-23T20:13:37Z) - HECT: High-Dimensional Ensemble Consistency Testing for Climate Models [1.7587442088965226]
Climate models play a crucial role in understanding the effect of environmental changes on climate to help mitigate climate risks and inform decisions.
Large global climate models such as the Community Earth System Model (CESM), are very complex with millions of lines of code describing interactions of the atmosphere, land, oceans, and ice.
Our work uses probabilistics like tree-based algorithms and deep neural networks to perform a statistically rigorous goodness-of-fit test of high-dimensional and man-made data.
arXiv Detail & Related papers (2020-10-08T15:16:16Z) - Generative Modeling for Atmospheric Convection [13.104272504735052]
We explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE)
VAE performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields on 6*106 samples spanning the globe.
It successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity.
arXiv Detail & Related papers (2020-07-03T00:24:09Z) - Hybrid modeling: Applications in real-time diagnosis [64.5040763067757]
We outline a novel hybrid modeling approach that combines machine learning inspired models and physics-based models.
We are using such models for real-time diagnosis applications.
arXiv Detail & Related papers (2020-03-04T00:44:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.