Introduction to Aviation Data Science with Machine Learning – Online Short Course (Starts Sept 27, 2022) 27 September - 3 November 2022 Online

Register Now

Intro to Aviation Data Science














Instructed by the Machine Learning group at the Universities Space Research Association with Dr. Ata Akbari Asanjan and Dr. Tejas Puranik

  • Sept 27, 2022- Nov 3, 2022 (6 Weeks, 12 Lectures/Labs, 24 Total Hours)
  • Every Tuesday and Thursday at 1300-1500 Eastern Time (all sessions will be recorded and available for replay; course notes will be available for download)
  • Learn how to deploy machine learning to solve challenging real-world problems in aviation using Python and JupyterLabs
  • All students will receive an AIAA Certificate of Completion at the end of the course

Overview
Data science and machine learning techniques have become more practice in recent years, and provide the potential to improve airspace operations and system-wide safety in aviation.  For example, machine learning techniques provide the potential to automatically identify emerging vulnerabilities in an aviation system by recognizing unusual operations that deviate from nominal operations.

This course teaches you fundamentals of reproducible data science and analytic, probabilistic reasoning and statistical inference, and machine learning to leverage data generated within the large scope of aviation and aeronautics. We will tackle several aviation related problems from a data-driven perspective and would learn how to propose solutions using machine learning and statistical inference. We learn how to deploy proper visualization tools, statistical inference, supervised learning (regression and classification), and unsupervised reasoning to solve problems related to air traffic management, airport surface operations, and flight operations.

Course will be taught in two phases: (i) lecture and discussion on the topic of interest, and (ii) lab, with implementation of the methods learned on the real-world data using Python in Jupyter Lab on the cloud.

Learning Objectives 

  • Become familiar with aviation domain data and problems.
  • Learn basics of data science and statistical inference.
  • Learn fundamentals of machine learning and how to properly solve a problem using ML.
  • Learn how to implement data science and machine learning solutions in Python on the cloud.
  • Gain experience using Python and JupyterLabs for collaborative data science projects.

Who Should Attend
This course is intended for researchers, engineers, academics, practitioners, and graduate students who not only want to get a deeper understanding of machine learning, but also want to learn on how to deploy machine learning to solve challenging real-world problems in aviation. The course is very hands-on in coding and implementations in Python. Program managers are encouraged to audit. 
 

Course Fees (Sign-In to Register)
AIAA Member Price: $995 USD
Non-Member Price: $1195 USD
AIAA Student Member Price: $495 USD

Classroom hours / CEUs: 24 classroom hours / 2.4 CEU/PDH

Cancellation Policy: A refund less a $50.00 cancellation fee will be assessed for all cancellations made in writing prior to 10 days before the start of the event. After that time, no refunds will be provided.


Contact:
  Please contact Lisa Le or Customer Service if you have any questions about the course or group discounts.

Outline
Week Lecture Coding Lab
Class 1 Intro to data science and linear algebra review Implementation of linear algebra in Python with Numpy.
Class 2-3 Data exploration and visualization Real data exploration with Pandas and data visualization with Matplotlib and Folium on a case study of flight’s landing.
Class 3-4 Probability and statistics Probabilistic reasoning and simple aggregate statistics with synthetic data and time-based flow management (TBFM) data.
Class 5 Linear regression, supervised machine learning and cross validation Application of linear regression for supervised anomaly detection in flight’s operational data.
Class 6-7 Multiple linear regression, data pre-processing and hyper-parameter tuning Multiple linear regression with and without regularization on a case study of predicting duration of the flight.
Class 8 Bayesian vs frequentist: classification with Naïve Bayes Arrival runway prediction with Naïve Bayes on the TBFM data.
Class 9 K-Nearest Neighbor, imbalanced datasets, and feature importance Application of KNN for anomaly detection in flight’s operational data during take-off of commercial aircraft.
Class 10 Classification and Regression with Support Vector Machines Application of SVM for supervised anomaly detection in flight’s operational data and predicting duration of the flight.
Class 11 Unsupervised machine learning: clustering with K-Means, and dimensionality reduction with Principal Component Analysis (PCA) Unsupervised analysis of air traffic data as well as flight’s operational data.
Materials

Course Delivery and Materials

  • The course lectures will be delivered via Microsoft Teams. You can test your connection here: https://support.microsoft.com
  • The coding labs will be delivered on the cloud using USRA’s cloud computing resources. You will receive login information and instructions after registration.
  • Access to the MS Teams classroom will be provided to registrants near to the course start date.
  • All sessions will be available on-demand within 1-2 days of the lecture. Once available, you can stream the replay video anytime, 24/7.
  • All slides will be available for download after each lecture. No part of these materials may be reproduced, distributed, or transmitted, unless for course participants. All rights reserved. USRA Proprietary.
  • Between lectures during the course, the instructor(s) will be available via email for technical questions and comments.

Instructors

Instructors


Dr. Ata Akbari Asanjan is an interdisciplinary data scientist in the Environmental Analytics Group of the Universities Space Research Association’s (USRA’s) Research Institute for Advanced Computer Science (RIACS), who works in close collaboration with the Data Science and Aviation Systems Groups at NASA’s Ames Research Center. Dr. Asanjan’s research currently is focused on machine learning and artificial intelligence for environmental and aviation applications. In addition to being an instructor for introductory and advanced aviation data science courses, he is also leading USRA’s environmental data science curriculum initiative working in close collaboration with the NASA Data Science and Aviation Systems Groups. Dr. Asanjan holds a Ph.D. in Civil Engineering from the University of California, Irvine, with a thesis focused on application of machine learning in forecasting rainfall.


Dr. Tejas Puranik is a senior scientist at the Universities Space Research Association’s (USRA’s) Research Institute for Advanced Computer Science (RIACS), who works in close collaboration with the Aviation Systems Division at NASA’s Ames Research Center. He holds a Ph.D. in Aerospace Engineering from the Georgia Institute of Technology. Dr. Puranik’s current research is mainly focused on application of machine learning and artificial intelligence for air traffic management and trajectory prediction applications in aviation. He has past experience in applying machine learning techniques to problems in aviation safety and sustainability.

 

 

AIAA Training Links