Machine Learning in Python for Environmental Science Problems

Sunday, 6 January 2019, 8:30 a.m.–3:45 p.m.
Phoenix Convention Center 223

 

AGENDA

 

AMS Short Course on Machine Learning in Python for Environmental Science Problems

6 January 2019, Phoenix, AZ

 

Max Capacity has been reached (sold out)

 

The AMS Short Course on Machine Learning in Python for Environmental Science Problems will be held on Sunday January 6, 2019, preceding the 99th AMS Annual Meeting in Phoenix, Arizona. Preliminary programs, registration, hotel, and general information will be posted on the AMS Annual Meeting Website (https://annual.ametsoc.org/) in mid-September 2018.

 

Interest in artificial intelligence, machine learning, and deep learning in the environmental sciences has grown rapidly in conjunction with the increased presence of AI in our daily lives. Many people now want to apply machine learning to their own data and problems but do not know where to start. The goal of this course is to teach participants how to develop a machine-learning workflow, using open-source Python tools to solve common types of problems in the atmospheric, oceanic, and environmental sciences.

 

Specifically, this short course will teach participants how to use Python machine-learning and deep-learning libraries to process a dataset, train different models, generate and evaluate predictions for previously unseen cases, and interpret models to gain physical understanding of what they have learned.

 

Participants will use a series of Jupyter notebooks to explore severe weather data, train various machine-learning models, and interact with Python’s machine-learning pipeline with a focus on xarray, pandas, scikit-learn, and Tensorflow. The notebooks will be hosted on a cloud-computing service with access to graphical processing units (GPUs), which will enable participants to train and interpret deep learning models in real-time.

 

All participants need to bring a laptop with a power adapter and the ability to connect wirelessly to the internet via the conference center network. Participants should have a basic understanding of the Python programming language, but no previous machine learning or data science experience is required. Additional instructions will be emailed to registered participants before the course begins. 

 

The instructors for this course are:

David John Gagne II, National Center for Atmospheric Research, Boulder, Colorado

Sheri Mickelson, National Center for Atmospheric Research, Boulder, Colorado

Ryan Lagerquist, University of Oklahoma, Norman, Oklahoma

Greg Herman, Colorado State University, Fort Collins, Colorado

 

A lunch will be provided during the short course.

 

For more information please contact David John Gagne at the National Center for Atmospheric Research, P.O. 3000, Boulder, CO 80307 (email: dgagne@ucar.edu, phone: 303-497-2714, Twitter: @DJGagneDos)

Short Course/Workshop Registration

All short course/workshop attendees must register and wear a badge/ribbon. Short course/workshop registration is not included in the 99th Annual Meeting registration, and short course/workshop registration does not include registration for the 99th AMS Annual Meeting.

view registration rates