Publication

Probabilistic Deep Learning on Spheres for Weather/Climate Applications

2020
Student Projects

Abstract

This work presents the application of a probabilistic approach to an already existing deep learning model for weather and climate prediction. Probabilistic deep learning allows to capture and address the uncertainties related to the data given as input and the uncertainties related to the model itself. Several models are explored : Deep Ensembling, Stochastic Weight Averaging (SWA), Stochastic Weight Averaging Gaussian (SWAG), MultiSWA and MultiSWAG. Experimental results show that using any of the mentioned models outperforms the deterministic, non-probabilistic model.

Official source

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2020
Student Projects

Abstract

Official source

Related concepts (32)

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Numerical weather prediction

Numerical weather prediction (NWP) uses mathematical models of the atmosphere and oceans to predict the weather based on current weather conditions. Though first attempted in the 1920s, it was not until the advent of computer simulation in the 1950s that numerical weather predictions produced realistic results. A number of global and regional forecast models are run in different countries worldwide, using current weather observations relayed from radiosondes, weather satellites and other observing systems as inputs.

Weather

Weather is the state of the atmosphere, describing for example the degree to which it is hot or cold, wet or dry, calm or stormy, clear or cloudy. On Earth, most weather phenomena occur in the lowest layer of the planet's atmosphere, the troposphere, just below the stratosphere. Weather refers to day-to-day temperature, precipitation, and other atmospheric conditions, whereas climate is the term for the averaging of atmospheric conditions over longer periods of time.

Related publications (32)

Probabilistic Deep Learning on Spheres for Weather/Climate Applications

Chat with Graph Search

Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM)

Learning and Control with Generalization and Stability Certificates

Fundamental Limits and Solvable Models of Feature Learning in High-Dimensional Models and Attention Networks