Learning to forecast diagnostic parameters using pre-trained weather embedding
Dec 15, 2023
Speakers
Peetak Mitra
Speaker · 0 followers
Vivek Ramavajjala
Speaker · 0 followers
About
Data-driven weather prediction (DDWP) models are increasingly becoming popular for weather forecasting. While DDWPs primarily forecast prognostic parameters, many diagnostic meteorological parameters (such as precipitation) are dependent on the most recent weather state and are modeled by learning a data-driven functional mapping of the current meteorological state (c.f. FourCastNet). However, the cost of training bespoke models for diagnostic variables can scale significantly and further limit the use during operationalizing these forecasts. This presents an opportunity to learn dense representations of essential meteorological parameters in a latent space, and using learned representations to model diagnostic parameters, or any other dependent variables. Using learned representations of weather allows for efficient prediction of dependent variables, while dramatically lowering the training cost for such models as well. In this paper, we present one such weather embedding model, WeatherX, trained on decades of reanalysis data that is used to train multiple diagnostic variables. The results indicate that models trained using learned representations of weather offer performance comparable to bespoke models, while leading to significant reduction in resource utilization during training and inference. Further lower memory footprint during operationalization leads to additional gain of running larger ensembles during inference thereby further improving uncertainty quantification of the said forecasts.Data-driven weather prediction (DDWP) models are increasingly becoming popular for weather forecasting. While DDWPs primarily forecast prognostic parameters, many diagnostic meteorological parameters (such as precipitation) are dependent on the most recent weather state and are modeled by learning a data-driven functional mapping of the current meteorological state (c.f. FourCastNet). However, the cost of training bespoke models for diagnostic variables can scale significantly and further limit…
Organizer
NeurIPS 2023
Account · 644 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Polynomially Over-Parameterized Convolution Neural Networks Contain Structured Strong Winning Lottery Tickets
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
Watch later
Siliang Zeng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Perspectives on knowledge acquisition and mobilization with neural networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
IVRE: Interactive Visual Reasoning under Uncertainty
Watch later
Manjie Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Zero-One Laws of Graph Neural Networks
Watch later
Sam Adam-Day, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Supervising Variational Autoencoder Latent Representations with Language
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%