Dynamical Tests of a Deep-Learning Weather Prediction Model
- URL: http://arxiv.org/abs/2309.10867v1
- Date: Tue, 19 Sep 2023 18:26:41 GMT
- Title: Dynamical Tests of a Deep-Learning Weather Prediction Model
- Authors: Gregory J. Hakim and Sanjit Masanam
- Abstract summary: Deep-learning weather prediction models have been shown to produce forecasts that rival those from physics-based models run at operational centers.
It is unclear whether these models have encoded atmospheric dynamics, or simply pattern matching that produces the smallest forecast error.
Here we subject one such model, Pangu-weather, to a set of four classical dynamical experiments that do not resemble the model training data.
We conclude that the model encodes realistic physics in all experiments, and suggest it can be used as a tool for rapidly testing ideas before using expensive physics-based models.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Global deep-learning weather prediction models have recently been shown to
produce forecasts that rival those from physics-based models run at operational
centers. It is unclear whether these models have encoded atmospheric dynamics,
or simply pattern matching that produces the smallest forecast error. Answering
this question is crucial to establishing the utility of these models as tools
for basic science. Here we subject one such model, Pangu-weather, to a set of
four classical dynamical experiments that do not resemble the model training
data. Localized perturbations to the model output and the initial conditions
are added to steady time-averaged conditions, to assess the propagation speed
and structural evolution of signals away from the local source. Perturbing the
model physics by adding a steady tropical heat source results in a classical
Matsuno--Gill response near the heating, and planetary waves that radiate into
the extratropics. A localized disturbance on the winter-averaged North Pacific
jet stream produces realistic extratropical cyclones and fronts, including the
spontaneous emergence of polar lows. Perturbing the 500hPa height field alone
yields adjustment from a state of rest to one of wind--pressure balance over ~6
hours. Localized subtropical low pressure systems produce Atlantic hurricanes,
provided the initial amplitude exceeds about 5 hPa, and setting the initial
humidity to zero eliminates hurricane development. We conclude that the model
encodes realistic physics in all experiments, and suggest it can be used as a
tool for rapidly testing ideas before using expensive physics-based models.
Related papers
- Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model [0.0]
Thunderstorms have significant social and economic impacts due to heavy precipitation, hail, lightning, and strong winds.
We develop SALAMA 1D, a deep neural network that directly infers the probability of thunderstorm occurrence from vertical profiles of ten atmospheric variables.
SALAMA 1D is trained over Central Europe with lightning observations as the ground truth.
arXiv Detail & Related papers (2024-09-30T08:40:28Z) - Robustness of AI-based weather forecasts in a changing climate [1.4779266690741741]
We show that current state-of-the-art machine learning models trained for weather forecasting in present-day climate produce skillful forecasts across different climate states.
Despite current limitations, our results suggest that data-driven machine learning models will provide powerful tools for climate science.
arXiv Detail & Related papers (2024-09-27T08:11:49Z) - Exploring the Potential of Hybrid Machine-Learning/Physics-Based Modeling for Atmospheric/Oceanic Prediction Beyond the Medium Range [0.0]
This paper explores the potential of a hybrid modeling approach that combines machine learning (ML) with conventional physics-based modeling for weather prediction beyond the medium range.
The model is based on the low-resolution, simplified parameterization atmospheric general circulation model (AGCM) SPEEDY.
The model has skill in predicting the El Nino cycle and its global teleconnections with precipitation for 3-7 months depending on the season.
arXiv Detail & Related papers (2024-05-29T20:56:44Z) - Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which Generalizes weather forecasts to Finer-grained Temporal scales.
Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale.
We introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
arXiv Detail & Related papers (2024-05-22T16:21:02Z) - Aurora: A Foundation Model of the Atmosphere [56.97266186291677]
We introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data.
In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts.
arXiv Detail & Related papers (2024-05-20T14:45:18Z) - ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs [14.095897879222676]
We present ClimODE, a continuous-time process that implements key principle of statistical mechanics.
ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow.
Our approach outperforms existing data-driven methods in global, regional forecasting with an order of magnitude smaller parameterization.
arXiv Detail & Related papers (2024-04-15T06:38:21Z) - Weather Prediction with Diffusion Guided by Realistic Forecast Processes [49.07556359513563]
We introduce a novel method that applies diffusion models (DM) for weather forecasting.
Our method can achieve both direct and iterative forecasting with the same modeling framework.
The flexibility and controllability of our model empowers a more trustworthy DL system for the general weather community.
arXiv Detail & Related papers (2024-02-06T21:28:42Z) - 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 ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples.
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-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation [67.20588721130623]
We develop an AI-based cyclic weather forecasting system, FengWu-4DVar.
FengWu-4DVar can incorporate observational data into the data-driven weather forecasting model.
Experiments on the simulated observational dataset demonstrate that FengWu-4DVar is capable of generating reasonable analysis fields.
arXiv Detail & Related papers (2023-12-16T02:07:56Z) - An evaluation of deep learning models for predicting water depth
evolution in urban floods [59.31940764426359]
We compare different deep learning models for prediction of water depth at high spatial resolution.
Deep learning models are trained to reproduce the data simulated by the CADDIES cellular-automata flood model.
Our results show that the deep learning models present in general lower errors compared to the other methods.
arXiv Detail & Related papers (2023-02-20T16:08:54Z)
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.