WELCOME TO THE DISASTER DATA SCIENCE LAB

We are a group of data scientists and trainees who research how to leverage data to help others before, during, and after disasters. Globally, frequency and intensity of disasters are rising. We tackle pressing and challenging problems of disaster research by collecting and analyzing data to suggest evidence-based remedies.

1280px-Katia,_Irma,_Jose_2017-09-08_1745Z–1935Z.jpg
 
Cascadia Rising 2022 ArcGIS Story map.png

ASSESSING THE EXPECTATIONS GAP: IMPACT ON CRITICAL INFRASTRUCTURE SERVICE PROVIDERS AND CONSUMERS PREPAREDNESS, AND RESPONSE

Community lifeline service providers and local emergency managers must maintain coordinated response and recovery plans. However, their timelines may not match expectations of local consumers of lifeline services. It is likely that consumers have unrealistic expectations about lifeline restoration, which could explain current inadequate levels of disaster preparedness. This hypothesized expectation gap has received little attention. This interdisciplinary project will provide government agencies, lifeline providers, and consumers with strong evidence to address the expectations gap and, in turn, promote appropriate preparedness actions that will increase community resilience. (Image Credit: Cascadia Rising 2022 Public-Private Partnership)
Support: National Science Foundation (CMMI-2211077)

Integration-social-sci-ABM.png

CONCEPTUALIZING INTERORGANIZATIONAL PROCESSES FOR SUPPORTING INTERDEPENDENT LIFELINE INFRASTRUCTURE RECOVERY

Pacific Northwest infrastructures are under-prepared for the Cascadia subduction zone (CSZ) earthquake (magnitude 9.0+), with a 7-15% probability over the next 45 years or so. It likely will destroy or damage many infrastructures at the same time. The aim of this research is to transform how the U.S. prepares for the next CSZ earthquake, by improving coordinated preparedness and recovery of interdependent infrastructures after the earthquake, and informing how these interdependent infrastructures are designed, developed, and maintained to enhance their resilience and sustainability.
Support: National Science Foundation (BCS-2121616)

RAPID_press_release_street_view.jpg

THE COVID-19 PANDEMIC SEATTLE STREET VIEW CAMPAIGN

This project conducts longitudinal (repeat) street view surveys for 12 months across a broad cross-section of Seattle to collect data on the community impact of the pandemic. This project also develops and implements a series of open-source routines that automatically process the data to rapidly extract time-sensitive insights from the imagery. This project was featured by the UW News and several media outlets.
Support: National Science Foundation (CMMI-2031119)

HDBE_recovery_curves.png

PARTICIPATORY STATISTICAL INFERENCE OF INTERDEPENDENT CRITICAL INFRASTRUCTURE RECOVERY TIMES

The project will innovate a new methodological framework, as well as software tools to support this framework, for estimating post-event interdependent critical infrastructure recovery times. The core of the framework is a participatory process for eliciting recovery estimates from topical experts.
Support: National Science Foundation (CMMI-1824681)

CIC_density_approximation.png

DATA-ENABLED ACCELERATION OF STOCHASTIC COMPUTATIONAL EXPERIMENTS

This project will develop methods to accelerate stochastic computational experiments with the aid of heterogeneous data (for example, empirical observations, multi-fidelity simulations, and expert knowledge). These methods will help overcome the computational challenge associated with investigating unusual strings of events (for example, nuclear meltdown, cascading blackout, and epidemic outbreak) that are critical to the nation's economy, security, and health.
Support: National Science Foundation (DMS-1952781)

2018_DSSG_Figure.jpg

AUTOMATIC DAMAGE DETECTION ON POST-HURRICANE SATELLITE IMAGERY

The governing research question of the project is: Can a machine learning algorithm automatically annotate damages on post-hurricane satellite images? To answer the question, the project uses satellite imagery data on the Greater Houston area after Hurricane Harvey in 2017, and damage labels created by crowdsourcing. The left-hand side image shows crowdsourced labels (1: Flooded/Damaged; 2: Non-damaged) and the right-hand side image shows our algorithm's prediction. For more information, please see the project website, presentation videoslides, and GitHub repo.
Support: Data Science for Social Good Program of the eScience Institute

Strava_Heatmap_Santa_Rosa_2017-2018_aggr

BUILDING BACK BETTER: INNOVATIVE METHODS TO MEASURE RESILIENCE

During the disaster recovery process, it is extremely challenging to continuously assess community health and well-being. Readily available data sources on community health and wellbeing during the disaster recovery period are essential to assessing community recovery of health and wellbeing and to building capacity for community resilience. This study aims to understand if and how data from personal health monitoring devices and apps, such as Fitbit and Strava, can be used to understand community resilience and inform recovery activities in the recovery period. This project is an interdisciplinary collaboration with the Collaborative on Extreme Event Resilience. (Image credit to Strava Global Heatmap: Santa Rosa's aggregated, public activities for 2017-2018)
Support: Population Health Initiative of the University of Washington

 
2018-Winter-End-Quarter-Meeting-2-28-2018.jpg

PEOPLE

 
Youngjun_Choe_2017.jpg

Lab Director &
Associate Professor

Ph.D. (2016) Industrial & Operations Engineering
University of Michigan

M.A. (2016) Statistics
University of Michigan

B.S. (2010) Physics & Management Science
KAIST, Korea  

WP_20160316_16_15_23_Pro.jpg

Graduate Researcher
(2019/9 – Present)

Ph.D. Student (2019 - Present)

Industrial & Systems Engineering
University of Washington

B. Eng. (2019)
Industrial & Systems Engineering
University of Minnesota

Nick Terry.jpeg

Graduate Researcher
(2019/9 – Present)

Ph.D. Student (2019 - Present)

Industrial & Systems Engineering
University of Washington

B.S. (2017)
Industrial & Systems Engineering

(Operations Research Concentration)

Georgia Institute of Technology

Christopher Salazar.PNG

Graduate Researcher
(2020/8 – Present)

Registered Professional Engineer (California)

M.Sc. (2021) & Ph.D. Student (2021 - Present)

Industrial & Systems Engineering
University of Washington

B.S. (2013) & M.S. (2015) 

Civil and Environmental Engineering

University of California, Davis

Ribhu Sengupta.png

Graduate Researcher
(2022/6 – Present)

Ph.D. Student (2022 - Present)
Industrial & Systems Engineering
University of Washington
M.S. (2021) Statistics
Georgia Institute of Technology

B.S. (2018) 
Industrial & Systems Engineering
Georgia Institute of Technology

Ly_Megan_Headshot.png

Undergraduate Researcher
(2019/11 – Present)

B.Sc. (exp. 2023)

Human Centered Design & Engineering
University of Washington

Emily Whelan.jpg

EMILY WHELAN

Undergraduate Researcher
(2021/1 – Present)

B.Sc. (2022)

Industrial & Systems Engineering
University of Washington

Iris Zhou.jpg

Undergraduate Researcher
(2022/9 – Present)

B.Sc. (exp. 2024)

Mathematics
University of Washington

Graduate Alumni:

  • Ivan Iturriaga, M.Sc. in Industrial Engineering, Graduate Researcher (2021-2022).

  • Rosie Sun, M.Sc. in Biostatistics, ​Graduate Researcher (2020).

  • Quoc Dung (Daniel) Cao, Ph.D. in Industrial Engineering, Graduate Researcher (2017-2020).

  • Zhanlin (Kevin) Liu, Ph.D. in Industrial Engineering, Graduate Researcher (2016-2020).

  • Chris Haberland, M.Sc. in Computational Linguistics, Graduate Researcher (2018-2020).

  • Mary Barnes, M.A. in International Studies, Volunteer Data Scientist (2017-2018).

  • Zach McCauley, M.Sc. in Industrial Engineering, Graduate Researcher (2017-2018).

Undergraduate Alumni:

  • Varun Agrawal, B.Sc in Computer Science, Undergraduate Researcher (2022).

  • Tommy Zhang, B.Sc. in Industrial Engineering, Undergraduate Researcher (2022).

  • Glenndi Tjuandi, B.Sc. in Industrial Engineering, Undergraduate Researcher (2021-2022).

  • Vanessa Yang, B.Sc. in Statistics and Informatics, Undergraduate Researcher (2020-2021).

  • Patricia Nathania Rustam, B.Sc. in Industrial Engineering, Undergraduate Researcher (2020-2021).

  • Jennifer Helga Mulia, B.Sc. in Industrial Engineering (Computational Finance Risk Management Minor), Undergraduate Researcher (2021).

  • Valentina Valero Nieto, B.Sc. in Industrial Engineering, Undergraduate Researcher (2020).

  • Aman Ankit, B.Sc. in Industrial Engineering, Undergraduate Researcher (2017-2020).

  • Ken Yamada, B.Sc. in Industrial Engineering, Undergraduate Researcher (2019-2020).

  • Summer Ai, B.Sc. in Statistics & Psychology, Undergraduate Researcher (2018-2019).

  • Amy Xu, B.Sc. in Computer Science, Undergraduate Researcher (2017-2018).

  • Trevor J. Aquiningoc, B.Sc. in Mechanical Engineering, Undergraduate Researcher (2018).

  • Yu-Ting Chen, B.Sc. in Statistics & Economics, Undergraduate Researcher (2017-2018).

  • Xiaoyan Peng, B.Sc. in Statistics & Economics, Undergraduate Researcher (2017-2018).

  • Danni Shi, B.Sc. in Statistics, Undergraduate Researcher (2017-2018).

  • Aryton Tediarjo, B.Sc. in Industrial Engineering, Undergraduate Researcher (2017-2018).

  • Dengxian (Dara) Yang, B.Sc. in Applied & Computational Math Sci., Undergraduate Researcher (2017-2018).

  • Ty Good, B.Sc. in Industrial Engineering, Undergraduate Researcher (2017-2018).

  • Li Ding, B.Sc. in Industrial Engineering, Undergraduate Researcher (2017-2018).

  • Zechariah Cheung, B.Sc. in Computer Science, Undergraduate Researcher (2017-2018).

  • Nick Monsees, B.Sc. in Computer Engineering, Undergraduate Researcher (2017-2018).

  • Xuejiao Li, B.Sc. in Applied Physics & Applied Mathematics (Minor), Undergraduate Researcher (2017-2018).  

  • Megan Miyasaki, B.Sc. in Physics, Undergraduate Researcher (2017-2018).

  • Christine Dien,  B.Sc. in Bioengineering, Undergraduate Researcher (2017-2018).

  • Randy Christopher Wenan, B.Sc. in Industrial Engineering,  Undergraduate Researcher (2017-2018).

  • Daniel Colina,  B.Sc. in Informatics, Undergraduate Researcher (2017-2018)

  • Winter Meng, B.Sc. in Applied Physics & Applied Math, Undergraduate Researcher (2017-2018).


Openings: If you would like to be considered for participating in our lab's research, please send Prof. Choe an email with your resume and (unofficial) transcript. Those from traditionally underrepresented groups in STEM (e.g., women and minorities) are particularly encouraged to get in touch.

News

  • 11/7/2022: Youngjun Choe (director) receives the NETI Educational Development Award from the UW College of Engineering.

  • 5/27/2022: Emily Whelan (undergraduate researcher) is selected as a Dean's Medal Nominee at the UW College of Engineering.  

  • 4/29/2022: Youngjun Choe (director) receives the Faculty Appreciation for Career Education & Training (FACET) Recognition from the UW Career Center @ Engineering.

  • 7/30/2020: Youngjun Choe (director) is selected as a Fellow of the NSF-supported Operations and Systems Engineering Extreme Event Research (OSEEER) network’s Early Career Mentoring (ECM) program.

  • 10/21/2019: Zhanlin (Kevin) Liu (graduate researcher) is selected as the INFORMS QSR Best Paper Competition Finalist.

  • 5/20/2019: Aman Ankit (undergraduate researcher) and his research appear in the UW ISE News.

  • 11/5/2018: Daniel Cao Quoc Dung (graduate researcher) wins the 3rd place in the INFORMS Poster Competition at the INFORMS Annual Meeting, Phoenix, AZ and appears in the UW ISE News

CONTACT US

Aerospace & Engineering Research Building (AERB), 141F, Seattle, WA 98105

Prof. Youngjun Choe <ychoe@uw.edu>