Data driven weather forecasts trained and initialised directly from observations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: McNally, Anthony, Lessig, Christian, Lean, Peter, Boucher, Eulalie, Alexe, Mihai, Pinnington, Ewan, Chantry, Matthew, Lang, Simon, Burrows, Chris, Chrust, Marcin, Pinault, Florian, Villeneuve, Ethel, Bormann, Niels, Healy, Sean
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910537789472768
author McNally, Anthony
Lessig, Christian
Lean, Peter
Boucher, Eulalie
Alexe, Mihai
Pinnington, Ewan
Chantry, Matthew
Lang, Simon
Burrows, Chris
Chrust, Marcin
Pinault, Florian
Villeneuve, Ethel
Bormann, Niels
Healy, Sean
author_facet McNally, Anthony
Lessig, Christian
Lean, Peter
Boucher, Eulalie
Alexe, Mihai
Pinnington, Ewan
Chantry, Matthew
Lang, Simon
Burrows, Chris
Chrust, Marcin
Pinault, Florian
Villeneuve, Ethel
Bormann, Niels
Healy, Sean
contents Skilful Machine Learned weather forecasts have challenged our approach to numerical weather prediction, demonstrating competitive performance compared to traditional physics-based approaches. Data-driven systems have been trained to forecast future weather by learning from long historical records of past weather such as the ECMWF ERA5. These datasets have been made freely available to the wider research community, including the commercial sector, which has been a major factor in the rapid rise of ML forecast systems and the levels of accuracy they have achieved. However, historical reanalyses used for training and real-time analyses used for initial conditions are produced by data assimilation, an optimal blending of observations with a physics-based forecast model. As such, many ML forecast systems have an implicit and unquantified dependence on the physics-based models they seek to challenge. Here we propose a new approach, training a neural network to predict future weather purely from historical observations with no dependence on reanalyses. We use raw observations to initialise a model of the atmosphere (in observation space) learned directly from the observations themselves. Forecasts of crucial weather parameters (such as surface temperature and wind) are obtained by predicting weather parameter observations (e.g. SYNOP surface data) at future times and arbitrary locations. We present preliminary results on forecasting observations 12-hours into the future. These already demonstrate successful learning of time evolutions of the physical processes captured in real observations. We argue that this new approach, by staying purely in observation space, avoids many of the challenges of traditional data assimilation, can exploit a wider range of observations and is readily expanded to simultaneous forecasting of the full Earth system (atmosphere, land, ocean and composition).
format Preprint
id arxiv_https___arxiv_org_abs_2407_15586
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data driven weather forecasts trained and initialised directly from observations
McNally, Anthony
Lessig, Christian
Lean, Peter
Boucher, Eulalie
Alexe, Mihai
Pinnington, Ewan
Chantry, Matthew
Lang, Simon
Burrows, Chris
Chrust, Marcin
Pinault, Florian
Villeneuve, Ethel
Bormann, Niels
Healy, Sean
Atmospheric and Oceanic Physics
Machine Learning
Skilful Machine Learned weather forecasts have challenged our approach to numerical weather prediction, demonstrating competitive performance compared to traditional physics-based approaches. Data-driven systems have been trained to forecast future weather by learning from long historical records of past weather such as the ECMWF ERA5. These datasets have been made freely available to the wider research community, including the commercial sector, which has been a major factor in the rapid rise of ML forecast systems and the levels of accuracy they have achieved. However, historical reanalyses used for training and real-time analyses used for initial conditions are produced by data assimilation, an optimal blending of observations with a physics-based forecast model. As such, many ML forecast systems have an implicit and unquantified dependence on the physics-based models they seek to challenge. Here we propose a new approach, training a neural network to predict future weather purely from historical observations with no dependence on reanalyses. We use raw observations to initialise a model of the atmosphere (in observation space) learned directly from the observations themselves. Forecasts of crucial weather parameters (such as surface temperature and wind) are obtained by predicting weather parameter observations (e.g. SYNOP surface data) at future times and arbitrary locations. We present preliminary results on forecasting observations 12-hours into the future. These already demonstrate successful learning of time evolutions of the physical processes captured in real observations. We argue that this new approach, by staying purely in observation space, avoids many of the challenges of traditional data assimilation, can exploit a wider range of observations and is readily expanded to simultaneous forecasting of the full Earth system (atmosphere, land, ocean and composition).
title Data driven weather forecasts trained and initialised directly from observations
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2407.15586