Abstract
Abstract. Recently, there has been growing interest in the possibility of using neural networks for both weather forecasting and the generation of climate datasets. We use a bottom–up approach for assessing whether it should, in principle, be possible to do this. We use the relatively simple general circulation models (GCMs) PUMA and PLASIM as a simplified reality on which we train deep neural networks, which we then use for predicting the model weather at lead times of a few days. We specifically assess how the complexity of the climate model affects the neural network's forecast skill and how dependent the skill is on the length of the provided training period. Additionally, we show that using the neural networks to reproduce the climate of general circulation models including a seasonal cycle remains challenging – in contrast to earlier promising results on a model without seasonal cycle.
Highlights
Synoptic weather forecasting has for decades been dominated by computer models based on physical equations – the so-called numerical weather prediction (NWP) models
The network for pumat42, which is more complex than pumat21 but less complex than the two Planet Simulator (PLASIM) runs, lies in between
We have to note that at long lead times and near-zero anomaly correlation coefficient (ACC), RMSE can be hard to interpret since it can be strongly influenced by biases in the forecasts
Summary
Synoptic weather forecasting (forecasting the weather at lead times of a few days up to 2 weeks) has for decades been dominated by computer models based on physical equations – the so-called numerical weather prediction (NWP) models. The problem is a good candidate for supervised machine learning. Machine learning techniques have already been used to improve certain components of NWP and climate models – mainly parameterization schemes (Krasnopolsky and Fox-Rabinovitz, 2006; Rasp et al, 2018; Krasnopolsky et al, 2013; O’Gorman and Dwyer, 2018), to aid real-time decision making (McGovern et al, 2017) to exploit observations and targeted high-resolution simulations to enhance earth system models (Schneider et al, 2017), for El Niño predictions (Nooteboom et al, 2018), and to predict weather forecast uncertainty (Scher and Messori, 2018)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
