Residual Diffusion Modeling for Km-scale Atmospheric Downscaling
- URL: http://arxiv.org/abs/2309.15214v3
- Date: Sun, 10 Dec 2023 03:17:29 GMT
- Title: Residual Diffusion Modeling for Km-scale Atmospheric Downscaling
- Authors: Morteza Mardani, Noah Brenowitz, Yair Cohen, Jaideep Pathak, Chieh-Yu
Chen, Cheng-Chin Liu, Arash Vahdat, Karthik Kashinath, Jan Kautz, and Mike
Pritchard
- Abstract summary: A cost-effective downscaling model is trained from a high-resolution 2-km weather model over Taiwan.
textitCorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes.
Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to-km-scales machine learning weather predictions.
- Score: 51.061954281398116
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Predictions of weather hazard require expensive km-scale simulations driven
by coarser global inputs. Here, a cost-effective stochastic downscaling model
is trained from a high-resolution 2-km weather model over Taiwan conditioned on
25-km ERA5 reanalysis. To address the multi-scale machine learning challenges
of weather data, we employ a two-step approach Corrector Diffusion
(\textit{CorrDiff}), where a UNet prediction of the mean is corrected by a
diffusion step. Akin to Reynolds decomposition in fluid dynamics, this isolates
generative learning to the stochastic scales. \textit{CorrDiff} exhibits
skillful RMSE and CRPS and faithfully recovers spectra and distributions even
for extremes. Case studies of coherent weather phenomena reveal appropriate
multivariate relationships reminiscent of learnt physics: the collocation of
intense rainfall and sharp gradients in fronts and extreme winds and rainfall
bands near the eyewall of typhoons. Downscaling global forecasts successfully
retains many of these benefits, foreshadowing the potential of end-to-end,
global-to-km-scales machine learning weather predictions.
Related papers
- Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging [1.747339718564314]
This study illustrates the relative strengths and weaknesses of physics-based and AI-based approaches to weather prediction.
A hybrid NWP-AI system is proposed, wherein GEM-predicted large-scale state variables are spectrally nudged toward GraphCast predictions.
Results indicate that this hybrid approach is capable of leveraging the strengths of GraphCast to enhance the prediction skill of the GEM model.
arXiv Detail & Related papers (2024-07-08T16:39:25Z) - Validating Deep-Learning Weather Forecast Models on Recent High-Impact Extreme Events [0.1747623282473278]
We compare weather prediction models and ECMWF's high-resolution forecast (HRES) system in three case studies.
We find evidence that machine learning weather prediction models can achieve similar accuracy to HRES on record-shattering events.
However, extrapolating to extreme conditions may impact machine learning models more severely than HRES.
arXiv Detail & Related papers (2024-04-26T18:18:25Z) - Enhanced Precision in Rainfall Forecasting for Mumbai: Utilizing Physics Informed ConvLSTM2D Models for Finer Spatial and Temporal Resolution [0.0]
This study introduces deep learning spatial model aimed at enhancing rainfall prediction accuracy on a finer scale.
To test this hypothesis, we introduce a physics informed ConvLSTM2D model to predict precipitation 6hr and 12hr ahead for Mumbai, India.
arXiv Detail & Related papers (2024-04-01T13:56:12Z) - ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast.
We also introduce a training-free extreme value enhancement strategy named ExEnsemble, which increases the variance of pixel values and improves the forecast robustness.
Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
arXiv Detail & Related papers (2024-02-02T10:34:13Z) - Efficient Subseasonal Weather Forecast using Teleconnection-informed
Transformers [29.33938664834226]
Subseasonal forecasting is pivotal for agriculture, water resource management, and early warning of disasters.
Recent advances in machine learning have revolutionized weather forecasting by achieving competitive predictive skills to numerical models.
However, training such foundation models requires thousands of GPU days, which causes substantial carbon emissions.
arXiv Detail & Related papers (2024-01-31T14:27:35Z) - FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather
Forecasting [56.73502043159699]
This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution.
It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model.
The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
arXiv Detail & Related papers (2024-01-28T13:23:25Z) - Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies.
Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
arXiv Detail & Related papers (2023-11-30T08:22:08Z) - Rethinking Real-world Image Deraining via An Unpaired Degradation-Conditioned Diffusion Model [51.49854435403139]
We propose RainDiff, the first real-world image deraining paradigm based on diffusion models.
We introduce a stable and non-adversarial unpaired cycle-consistent architecture that can be trained, end-to-end, with only unpaired data for supervision.
We also propose a degradation-conditioned diffusion model that refines the desired output via a diffusive generative process conditioned by learned priors of multiple rain degradations.
arXiv Detail & Related papers (2023-01-23T13:34:01Z) - Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of
Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars.
They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
arXiv Detail & Related papers (2021-07-14T21:10:47Z) - TRU-NET: A Deep Learning Approach to High Resolution Prediction of
Rainfall [21.399707529966474]
We present TRU-NET, an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers.
We use a conditional-continuous loss function to capture the zero-skewed %extreme event patterns of rainfall.
Experiments show that our model consistently attains lower RMSE and MAE scores than a DL model prevalent in short term precipitation prediction.
arXiv Detail & Related papers (2020-08-20T17:27:59Z)
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.