The U.S. EPA Office of Research and Development in Cincinnati, Ohio is looking for a postdoc in Chemical Source Modeling Using Data Modeling, Statistics, and Machine Learning.  This link offers an “Apply” button for those that are interested,  I’ll copy the content below, although it doesn’t have the application link.  The announcement also lists an email address at Oak Ridge for administrative help, including about visas.  Applicants must have received their PhD in the last five years. 


I can answer some technical questions and put people in contact with the mentor, Dr. David Meyer. 


Best regards,






Raymond Smith

PhD Chemical Engineer

U.S. Environmental Protection Agency

National Risk Management Research Laboratory

26 W. Martin Luther King Drive

Cincinnati, OH 45268

[log in to unmask]




Chemical Source Modeling Using Data Mining, Statistics, and Machine Learning



U.S. Environmental Protection Agency (EPA)

Reference Code


How to Apply

A complete application consists of:

All documents must be in English or include an official English translation.

If you have questions, send an email to [log in to unmask].  Please include the reference code for this opportunity in your email.



This research project will develop methods to model sources of chemical releases throughout the life cycle of a chemical, including manufacturing, processing, distribution, use, and end-of-life activities, for application in human exposure models as part of the Agency’s high-throughput chemical risk assessment program. In collaboration with other ORD research, this research project will apply data mining, machine learning, and transport modeling principles to quickly and accurately estimate chemical releases.

The research project will involve the collection, curation, modeling, classification, regression, and prediction of chemical release data for risk assessment purposes. Collection will include searching for, extracting, documenting, and warehousing data throughout the world wide web. Curation will require evaluating and preprocessing data according to big data principles, with emphasis on data quality analysis. Modeling will involve the use of engineering knowledge to fill gaps in release data throughout the life cycles of chemicals. Classification refers to the use of machine learning to categorize collected data based on similarities in specified data descriptors, including physical properties, chemical quantities, and the nature of the activities involving the chemicals. Regression and other statistical methods will be applied as fit for purpose to model trends in the data. Prediction will be used as appropriate to extrapolate beyond the specific chemicals and circumstances studied in the previous steps. The research participant will interact with a team to develop methods and computer tools and to publish appropriate methodology and case study results.

The research participant will learn innovative ways to apply data mining and transport modeling skills within the field of chemical risk assessment to support next-generation high-throughput modeling approaches. The research participant will gain experience with the application of machine learning to big data for predictive analysis. The research participant will interact with leading exposure modelers and gain a better understanding of contemporary and emerging trends in human exposure modeling within a regulatory context. The research participant will learn about procedures for generating and managing high quality scientific data. The research participant will receive training on writing and publishing peer-reviewed research manuscripts. The research participant will have opportunities to learn about topics related to the primary research area of chemical risk assessment, such as materials management and sustainability, through interactions with various parts of the Agency.

This program, administered by ORAU through its contract with the U.S. Department of Energy (DOE) to manage the Oak Ridge Institute for Science and Education (ORISE), was established through an interagency agreement between DOE and EPA. The initial appointment is for one year, but may be renewed upon recommendation of EPA and is contingent on the availability of funds. The participant will receive a monthly stipend commensurate with educational level and experience. Proof of health insurance is required for participation in this program.

The appointment is full-time in the Cincinnati, Ohio area. Participants do not become employees of EPA, DOE or the program administrator, and there are no employment-related benefits. 



The qualified candidate must have received a doctoral level degree in one of the related fields. Degree must have been received within five years of the appointment start date.

A background and/or expertise with all or a combination of the following is desired: computer programming (Python, R), data mining, statistics and regression analysis, machine learning, chemical process modeling, transport phenomena modeling, and life-cycle inventory modeling. 


Eligibility Requirements