Interest in artificial intelligence, machine learning, and deep learning in the environmental sciences has grown rapidly in conjunction with the increased presence of these technologies 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. This 2-day virtual short course will develop your skills in applying Python libraries to process your data, train a variety of machine-learning models, generate predictions, and evaluate and interpret your trained models for physical understanding.

April 8 and 9, 2021 at 10:00 AM - 6:00 PM Eastern Time (Virtual)

REGISTRATION HAS REACHED CAPACITY FOR THIS COURSE

$64 for student members
$128 for members
$208 for non-members

Registration policy:

AMS requires a valid payment to be made within 5 days of the start of a course or sooner if registration has reached capacity. You will be contacted by AMS staff if payment is required. Refunds will not be issued to attendees within 7 days of the start of a course.

Course Description:

Interest in artificial intelligence (AI), machine learning (ML), and deep learning (DL) 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 ML to their own data and problems but do not know where to start. This 2-day short course will develop participants skills in applying python libraries to process their data, train a variety of ML models, generate predictions, and evaluate and interpret their trained models for physical understanding. 

Participants will interact with real-world data and the ML pipeline through a series of Google Collaboratory notebooks that will enable thorough exploration of the data and methods. Participant understanding of the concepts will be reinforced with hands-on exercises at the end of each lecture that require implementing many of the techniques introduced while grappling with the challenges of real-world environmental datasets.

Day one will cover AI and ML fundamentals and introduce Python libraries commonly employed for data analysis, ML, and deep learning (DL). Day two will provide participants with the option of instruction on more advanced topics in ML/DL following a similar lecture/exercise format as employed on day one. Additional?Instructions will be emailed to registered attendees before the course begins.

The goal of this course is to develop skills in applying machine learning to solve atmospheric, oceanic, and environmental science problems through a hands-on tutorial using open source Python tools.    

Participants in the course will complete the following objectives:  

• Pre-process environmental science data into a form amenable to machine learning (ML);
• Learn machine learning and data science fundamentals;
• Build and train machine learning and deep learning (DL) models;
• Evaluate machine learning model predictions with appropriate metrics and data;
• Interpret machine learning models for physical understanding; and
• Solidify understanding of the above topics through completion of hands-on, data-driven exercises.

This course is appropriate for those who are interested in ML and have some Python programming experience, but do not know how to apply ML techniques to their problem domains and datasets.

Instructors:

Amanda Burke

University of Oklahoma

William Chapman

University of California, San Diego

Callie McNicholas

University of Washington

Dylan J. Steinkruger

Pennsylvania State University

Hamid Kamangir

University of California, Davis

Tirthankar Chakraborty

Yale University

Mu-Chieh Ko

NOAA/AOML/HRD

David Hall

NVIDIA