Using machine learning to find cloud-base height: a didactic challenge
Lewis, Helena ; Bowyer, Jack ; Broad, Alistair Louis ; Chamberlain-Clay, Alex ; Jones, Caroline ; Chan, Steven ; Kahraman, Abdullah ; Morcrette, Cyril
Tutorials and example code, showing how to apply Machine Learning to image classification, are easy to find on the internet. What is less common are simple examples that are relevant to the atmospheric sciences. The purpose of this article is to document a small Machine Learning project carried out at the Met Office, with the purpose of providing a meteorologically relevant example of data preparation and training, followed by quantitative evaluation of performance.<br>We begin by introducing a simple atmospheric problem and describe the generation of training data and the development of some example code. Then, we document the challenge, where interested members of Met Office staff competed against each other to improve upon the basic code before coming together to produce this paper.</p>
Accès à la notice sur le site du portail documentaire de Météo-France