Deep learning for bias-correcting CMIP6-class Earth system models
- URL: http://arxiv.org/abs/2301.01253v3
- Date: Thu, 28 Sep 2023 13:04:18 GMT
- Title: Deep learning for bias-correcting CMIP6-class Earth system models
- Authors: Philipp Hess, Stefan Lange, Christof Sch\"otz and Niklas Boers
- Abstract summary: We show that a post-processing method based on physically constrained generative adversarial networks (cGANs) can correct biases of a state-of-the-art, CMIP6-class ESM.
While our method improves local frequency distributions equally well as gold-standard bias-adjustment frameworks, it strongly outperforms any existing methods in the correction of spatial patterns.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The accurate representation of precipitation in Earth system models (ESMs) is
crucial for reliable projections of the ecological and socioeconomic impacts in
response to anthropogenic global warming. The complex cross-scale interactions
of processes that produce precipitation are challenging to model, however,
inducing potentially strong biases in ESM fields, especially regarding
extremes. State-of-the-art bias correction methods only address errors in the
simulated frequency distributions locally at every individual grid cell.
Improving unrealistic spatial patterns of the ESM output, which would require
spatial context, has not been possible so far. Here, we show that a
post-processing method based on physically constrained generative adversarial
networks (cGANs) can correct biases of a state-of-the-art, CMIP6-class ESM both
in local frequency distributions and in the spatial patterns at once. While our
method improves local frequency distributions equally well as gold-standard
bias-adjustment frameworks, it strongly outperforms any existing methods in the
correction of spatial patterns, especially in terms of the characteristic
spatial intermittency of precipitation extremes.
Related papers
- GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
Diffusion models tend to reconstruct normal counterparts of test images with certain noises added.
From the global perspective, the difficulty of reconstructing images with different anomalies is uneven.
We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
arXiv Detail & Related papers (2024-06-11T17:27:23Z) - UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather [55.95708988160047]
LiDAR semantic segmentation (LSS) is a critical task in autonomous driving.
Prior LSS methods are investigated and evaluated on datasets within the same domain in clear weather.
We propose UniMix, a universal method that enhances the adaptability and generalizability of LSS models.
arXiv Detail & Related papers (2024-04-08T02:02:15Z) - Conditional diffusion models for downscaling & bias correction of Earth system model precipitation [1.5193424827619018]
We propose a novel machine learning framework for simultaneous bias correction and downscaling.
Our approach ensures statistical fidelity, preserves large-scale spatial patterns and outperforms existing methods.
arXiv Detail & Related papers (2024-04-05T11:01:50Z) - Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System
Model Fields with Generative Foundation Models [0.0]
We develop a consistency model (CM) that efficiently and accurately downscales arbitrary Earth system model (ESM) simulations without retraining in a zero-shot manner.
We show that the CM outperforms state-of-the-art diffusion models at a fraction of computational cost while maintaining high controllability on the downscaling task.
arXiv Detail & Related papers (2024-03-05T08:41:41Z) - Contrastive Learning for Climate Model Bias Correction and
Super-Resolution [0.0]
Post-processing is needed to make accurate estimates of local climate risk.
Here we propose an alternative approach to this challenge based on a combination of image super resolution (SR) and contrastive learning generative adversarial networks (GANs)
We find that our model successfully reaches a spatial resolution double that of NASA's product while also achieving comparable or improved levels of bias correction in both daily precipitation and temperature.
arXiv Detail & Related papers (2022-11-10T19:45:17Z) - Physically Constrained Generative Adversarial Networks for Improving
Precipitation Fields from Earth System Models [0.0]
Existing post-processing methods can improve ESM simulations locally, but cannot correct errors in modelled spatial patterns.
We propose a framework based on physically constrained generative adversarial networks (GANs) to improve local distributions and spatial structure simultaneously.
arXiv Detail & Related papers (2022-08-25T15:19:10Z) - Feature-Distribution Perturbation and Calibration for Generalized Person
ReID [47.84576229286398]
Person Re-identification (ReID) has been advanced remarkably over the last 10 years along with the rapid development of deep learning for visual recognition.
We propose a Feature-Distribution Perturbation and generalization (PECA) method to derive generic feature representations for person ReID.
arXiv Detail & Related papers (2022-05-23T11:06:12Z) - Decentralized Local Stochastic Extra-Gradient for Variational
Inequalities [125.62877849447729]
We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices.
We make a very general assumption on the computational network that covers the settings of fully decentralized calculations.
We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
arXiv Detail & Related papers (2021-06-15T17:45:51Z) - Value propagation-based spatio-temporal interpolation inspired by Markov
reward processes [0.06445605125467573]
We propose a propagation value method inspired by Markov reward processes (MRPs) as a spatial method.
We show that the average performance of SD-MRP on real-world data under all experimental conditions was ranked significantly higher than that of all other methods.
We further found that, even in cases where our methods had no significant advantage over baselines numerically, our methods preserved the structure of the target grid better than the baselines.
arXiv Detail & Related papers (2021-06-01T14:52:54Z) - 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) - PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and
Localization [64.39761523935613]
We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images.
PaDiM makes use of a pretrained convolutional neural network (CNN) for patch embedding.
It also exploits correlations between the different semantic levels of CNN to better localize anomalies.
arXiv Detail & Related papers (2020-11-17T17:29:18Z)
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.