Summer Series | Machine Learning Applications in Atmospheric Science
LOCATION
Summer Series | A fresh look at the RMetS virtual meetings of this season.
The RMetS Summer Series showcased previous virtual meetings by re-sharing the recordings from the events. You can watch these for free alongside other fellow academics and enthusiasts.
The Series ran during lunch times, providing a refreshing break every Wednesday in July and August.
If you have any questions regarding the Summer Series, please email meetings@rmets.org.
This is a showing of a previous Taster session presented by Samantha Adams.
ABSTRACT | In recent years the exploitation of Machine Learning in many different domains has expanded considerably due to the increasing availability of large datasets and compute power. Machine Learning is not a new concept to the atmospheric sciences and techniques such as Generalised Linear Modelling, clustering, dimension reduction and even Neural Networks have been in use for many years. However, in recent years new techniques within the Deep Learning field have made impressive progress in solving hard problems in challenging domains (for example, image classification, object recognition and natural language processing). These methods open new opportunities for the atmospheric sciences that may revolutionize some areas of model development, data assimilation, post-processing and data analysis. This talk will give a broad overview of some of the current application areas in the atmospheric sciences. Potential challenges with the adoption of Machine Learning into this domain are also discussed.
Summer Series | A fresh look at the RMetS virtual meetings of this season.
The RMetS Summer Series showcased previous virtual meetings by re-sharing the recordings from the events. You can watch these for free alongside other fellow academics and enthusiasts.
The Series ran during lunch times, providing a refreshing break every Wednesday in July and August.
If you have any questions regarding the Summer Series, please email meetings@rmets.org.
This is a showing of a previous Taster session presented by Samantha Adams.
ABSTRACT | In recent years the exploitation of Machine Learning in many different domains has expanded considerably due to the increasing availability of large datasets and compute power. Machine Learning is not a new concept to the atmospheric sciences and techniques such as Generalised Linear Modelling, clustering, dimension reduction and even Neural Networks have been in use for many years. However, in recent years new techniques within the Deep Learning field have made impressive progress in solving hard problems in challenging domains (for example, image classification, object recognition and natural language processing). These methods open new opportunities for the atmospheric sciences that may revolutionize some areas of model development, data assimilation, post-processing and data analysis. This talk will give a broad overview of some of the current application areas in the atmospheric sciences. Potential challenges with the adoption of Machine Learning into this domain are also discussed.