Home /   Seminars /   Aviation Data Science Lab Seminar Series

Aviation Data Science Lab Seminar Series

Seminar image

Aviation Data Science Lab Seminar Series

As the number of air vehicles grows with unmanned aerial systems and the amount of data grows in civil aviation, the future holds more promise for a greater impact from advanced tools and techniques in data science and AI. This Spring, learn from experts in government, industry, and academia in a 12-seminar series, sponsored by USRA and UC Berkeley with NASA Ames Research Center.

Duration: 12 seminars
Dates: January 22, 2020 - May 8, 2020
Time: Wednesdays 11:00 am - 12:00 pm (starting January 22, 2020)
Location: Seminars will take place at NASA's Ames Research Center (N210 R115) and UC Berkeley University Campus (105 Stanley Hall)
Link will be provided for live streaming for the weekly seminar


List of Seminar Speakers and Video Recordings

Designing aerial robots (and aerial taxis)
Date: TBD
Flying robots, such as multi-copters, are increasingly becoming part of our everyday lives, with current and future applications including personal transportation, delivery services, entertainment, and aerial sensing. These systems are expected to be safe and to have a high degree of autonomy. This talk will discuss the dynamics and control of multi-copters, with a focus on making these vehicles more robust to external disturbances, and component failures. We will discuss specific research results relating to increasing efficiency of the systems and overcoming range limitations, as well as design decisions that allow for greater robustness and safety in the face of component failures.
  • Assistant Professor, Mechanical Engineering, University of California, Berkeley
Advanced Aerial Mobility – Technological Drivers, Impacts, and Observations
Date: TBD
Technologies such as electric propulsion, composites manufacturing, and increasing autonomy are redefining flight. This is creating a renaissance in aviation. The fundamentally new capabilities in safe, simplified, low-cost, quiet, and vertical flight promise to vastly expand the use cases for flight to drive productivity across the economy, whether moving goods, moving people, or automating tasks. We will look at the drivers of this transformation, its historical context, and survey the broad implications it brings for the future. We will also address the opportunities this is creating today and entrepreneurial approaches to pushing toward realizing this vision.
  • Radius Capital, Managing Director
Data Science in Urban Air Mobility (UAM): Challenges and Opportunities
Date: April 29, 2020
Aviation is broadly a combination of aircraft, airspace and airports. The data science life cycle comprises of five steps - capture, maintain, process, analyze and communicate. The presentation introduces the legacy of conventional aviation research in the context of the data science life cycle to motivate the challenges with Urban Air Mobility, a field that is quite nascent. A summary of recent research will be presented to highlight the innovative ways to address the challenges. Examples provided will include the generation of synthetic data, encounter models from simulations, and leveraging novel and diverse data sets from traditional transportation and non-aviation sources, to analyze problems of operation in urban airspace. Finally, opportunities will be identified for further exploration, niche development and filling the gaps in the field of data science for UAM.
  • Aerospace Research Scientist, Crown Consulting Inc.
  • USRA NAMS Program at NASA Ames Research Center
  • Cal Unmanned Lab, Berkeley
Introduction to Air Traffic Management
Date: April 22, 2020
The presentation introduces Air Traffic Management with focus on air traffic data for data-science. Starting with the common attributes of transportation systems: highway transportation, air transportation and data transportation. The initial set of slides discuss the purpose of data-science in air traffic management, reasons why air traffic management is challenging, and the multidisciplinary nature of Air Traffic Management research. The history of flight from 1903 (Wright Flyer) to 1987, formation of the National Air Traffic Controllers Association is briefly discussed. The national airspace system is described in terms of airports in the U. S., air traffic control facilities (flight service stations, terminal, enroute and system command center), airspace geometry (sectors, airways and navaids), governing regulations and directives, airspace classification (Class A through G), special use airspace, visual flight rules and instrument flight rules. The contents of a flight-plan are described. Weather briefing is discussed. The surveillance equipment used for surface, terminal area and enroute are described, and the aircraft states obtained using the surveillance data are listed. Airline operations control functions: schedule development, flight planning, resource scheduling and flight following are noted. Next, the roles and responsibilities of air traffic controllers and traffic flow managers are discussed. Separation standards and conflict resolution techniques are outlined. Finally, traffic flow management techniques are reviewed with an illustrative example.
  • Senior Scientist, Crown Consulting Inc. at NASA Ames Research Center
Data Analytics for Flight Trajectories and Trajectory Anomalies
Date: April 15, 2020
Trajectory analysis is one of the canonical applications of data science to aviation. In this talk, Dr. Hansen will summarize some standard methods and recent research related to the analysis of flight trajectories. First, trajectory clustering methods will be overviewed and applied to identify common routes between selected US domestic city pairs. He will discuss feature engineering for trajectories in order to investigate how weather, winds, and traffic management initiatives affect the assignment of individual flights to different alternative routes. A generative model, which predicts the future evolution of a specific flight trajectory based on its flight plan, weather conditions, and trajectory history, will then be presented. Finally, he will consider the identification of “anomalous” trajectories with specific focus on the analysis and prediction of “go-arounds” of flights attempting to land at JFK airport.
  • University of California, Berkeley
Autonomy and Safety for Urban Air Mobility (UAM)
Date: March 4, 2020
Urban Air Mobility (UAM) can only be achieved at scale when emerging eVTOL operations are safe despite reduced pilot training requirements. Increased autonomy and access to new data pipelines are viewed as foundations to enable safe UAM operations. Traditional sensor data can be augmented with new cloud resources such as roadmaps and geographical information system (GIS) Lidar/video to offer emerging unmanned aircraft systems (UAS) and UAM operations a new level of situational awareness. This presentation will introduce challenges in UAM and summarize my group's research to identify, process, and utilize new data sources during nominal and emergency flight planning. Specific efforts have utilized machine learning to automatically map urban emergency landing sites, trade in-flight and landing site risks as needed, and incorporate cell phone data into an occupancy map. Research in flight safety assessment and management (FSAM) will be summarized; this work offers potential for improved resilience and increased verification for autonomous aircraft flight management. The presentation will end with videos illustrating recent small UAS flight testing in the University of Michigan's new M-Air netted flight facility.
  • Professor, Aerospace Engineering and Associate Director of Graduate Programs for the Robotics Institute of University of Michigan
Application of Machine Learning Techniques to Aviation Operations: NASA Case Studies
Date: February 26, 2020
There is an increasing interest in applying methods based on Machine Learning Techniques (MLT) to problems in aviation operations. The current interest is based on developments in Cloud Computing, the availability of open software and the success of MLT in automation, consumer behavior and finance involving large database. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. This talk describes issues to be addressed in applying either model-driven or data driven methods. Aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and a rich historical database are prime candidates for analysis using data-driven methods. The issues relating to data, feature selection and validation of the models are illustrated by examining case studies of the application of MLT to problems in air traffic management at NASA. Further research is needed in the application of MLT to critical aviation operations. As always, the best approach depends on the task, the physical understanding of the problem and the quality and quantity of the available data.
  • Principal Scientist, USRA, NASA Ames Research Center
Key Opportunities in Aeronautics Enterprise
Date: February 19, 2020
Aviation is growing and many new entrants are emerging. They include drones, urban air mobility vehicles, commercial space crafts, and high altitude platforms. Current airspace operations and air traffic management will have to evolve to accommodate them. At the same time, improvements in the current manned air traffic management operations are desired to reduce delays and increase capacity. The talk addresses how we can enable the future, while maintaining the safety operations that we enjoy. It will specifically discuss the needs for airspace access, scalability, safety, and efficiency of all airspace users. The talk begins with an anecdote on how the speaker got involved in air traffic management research and development, and ends with a discussion of why is it an exciting area for a new career.
  • Director, NASA Aeronautics Research Institute (NARI)
  • NASA’s Ames Research Center
Urban Computing for Planning Energy Efficient and Healthier Cities
Date: February 12, 2020

Dr. Gonzalez uses data science to characterize how humans interact with the built and the natural environment seeking to plan for more sustainable and livable cities. Given the increasing ubiquity of plug-in electric vehicles (PEVs) in the Bay Area, she presents a study that aims to assist in planning decisions by providing timing recommendations and assigning monetary values to modulations of PEV start and end charging times.

According to the US Energy Information Administration, the number of PEVs in the United States doubled between 2013 and 2015 and are expected to reach 20 million by 2020.

In the second part, Dr. Gonzalez presents DeepAir, a convolutional neural network platform that combines satellite imagery and urban maps with weather and air monitoring stations datasets. The goal is to enable science-informed policy by understanding various inter-dependencies in the quality of the air, we breathe. These methodologies are aimed to be fully scalable and open source. The presented methods can be extended to other domains that involve human and environmental interactions.

  • Associate Professor of City & Regional Planning, UC Berkeley
Predicting Gate Conflicts Using NASA ATD2 Fused Data Sources
Date: February 5, 2020
The modern day National Airspace System (NAS) is powered by System Wide Information Management (SWIM) which is a real-time digital data sharing infrastructure that provides a high fidelity view of the lifecycle of a flight. The newly available data within the SWIM feeds can be leveraged to help drive efficiencies in the NAS. In this talk, we investigate the gate conflict prediction problem as a concrete use case which could help drive efficiencies. We begin with a high level description of NASA's Airspace Technology Demonstration 2 which is built upon the real-time SWIM feeds and produces the data used in our investigation. We model gate conflicts as a regression problem and describe the iterative process of model building, model validation, and evaluation used to assess the efficacy of our approach. We quantify our predictive accuracy and identify paths for improvement. Through this iterative process we hope to evolve our models and methods in the development of a near real-time prediction service.
  • Aerospace Engineer, NASA Ames Research Center
Drone application development
Date: January 29, 2020
Sudip Mukhopadhyay, Ph.D. will discuss the drone application development, starting in 2007, of a select few customized end users applications. He will discuss lessons learned and innovative developments, which will augment the steps needed to make urban air mobility successful in the coming years. He will also describe the relevance and role of aerospace corporations versus today’s car manufacturers, and what we need to do to develop a new and successful alternative transportation ecosystem.
Sudip Mukhopadhyay, Ph.D.
  • Technologist, Business Finland
Aviation Data Science Seminar
Date: January 22, 2020
  • Professor, Civil Engineering, UC Berkeley

Program Committee

Organizing Committee

UC Berkeley Aviation Data Science Seminar

Point of Contact

Saba Hussain, Program Manager, USRA

The Aviation Data Science Seminar Series is a collaboration between USRA, NASA, and the University of California, Berkeley. For more information on the Aviation Data Science Lab at NASA Ames Research Center, please visit our web site.