[ES_JOBS_NET] US EPA Postdoctoral Research Program (Durham, NC): Mining complex data to uncover time-activity patterns and predict exposures to chemicals of concern

[Minucci, Jeffrey]

Mining complex data to uncover time-activity patterns and predict exposures to chemicals of concern

Project number:

CPHEA-08-02-2022-01

Lab/Center/Office:

CENTER FOR PUBLIC HEALTH & ENVIRONMENTAL ASSESSMENT

Division:

PUBLIC HEALTH & ENVIRONMENTAL SYSTEMS DIVISION

Branch:

EXPOSURE INDICATORS BRANCH

Brief description of research project:

Time activity patterns (TAPs) are widely used by environmental researchers and health professionals to estimate human exposure to, and health effects associated with, toxic substances (e.g., fluorinated chemicals, plasticizers, flame retardants, heavy metals). For example, estimates of PFAS exposures are impacted by time spent in different indoor locations, products used, and the frequency of cleaning. TAP data are traditionally collected through observational studies or activity pattern surveys, and the EPA's Exposure Factors Handbook synthesizes these data to present values for the general U.S. population. However, the costs and effort associated with these studies mean that data for specific communities or demographics may be unavailable or incomplete. Individual behaviors, household habits, and community characteristics can vary, which presents important considerations for quantifying human exposure to chemicals. Additionally, data from these studies may become outdated as time-activity patterns shift due to economic and social changes, including the SARS CoV-2 epidemic. As a result, there exists an incredible potential for artificial intelligence (e.g., machine learning [ML]) to advance our understanding of TAPs that mediate chemical exposures, by tapping into a variety of "big data" sources. The goal of this project is to develop data mining and ML-based approaches to collect and analyze publicly available big data including social media mentions and geotags, search engine trends, and consumer product purchase data. Using supervised and unsupervised ML techniques such as natural language processing and pattern recognition, we will identify meaningful geographic, demographic, and temporal trends in TAPs that inform how and when individuals are exposed to contaminants of concern.

Geographical location of position:

Research Triangle Park, NC

High priority research areas:

Chemicals of Emerging and Immediate Concern (SHC) Cumulative impacts (SHC, ACE)

Scientific project area:

Chemical exposure modeling, data science, data mining, human behavior

Educational requirements:

Ph.D. in Physical Sciences, Biology, Engineering, Computer Science, Applied Mathematics, or related field.

Specialized training and/or experience preferred:

Experience with data science (e.g., data mining, machine learning), statistics and programming in Python or R. Strong oral and written communication skills.

Projected duration of appointment:

3 years

Paid relocation to EPA work location:

Yes

Application Period Open Date:

Aug 02, 2022

Application Period Close Date:

Sep 01, 2022

Scientific contact/Principal Investigator(s)*:

Jeffrey Minucci, minucci.jeffrey at epa.gov

*This person/persons may be contacted for additional scientific information about this project. This person is not authorized to accept applications, make job offers, set salaries, establish start dates or discuss benefits.

For information on how to apply:

https://cfpub.epa.gov/ordpd/PostDoc_Lab.cfm?Lab=CPHEA

_______________________

Jeffrey Minucci (he/him)
Physical Scientist
Exposure Indicators Branch
Public Health and Environmental Systems Division
Center for Public Health and Environmental Assessment
US EPA | Office of Research and Development
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.ucar.edu/pipermail/es_jobs_net/attachments/20220815/b8d9911d/attachment-0001.htm>