Postdoctoral Position in Modeling Soil: The Department of Biosystems Engineering and Soil Science at the University of Tennessee-Knoxville is seeking a highly motivated individual for a grant-funded postdoctoral position. This role will focus on modeling soil greenhouse gas emissions, with a strong emphasis on nitrous oxide (N2O), data science, predictive modeling using machine learning and deep learning, or a related discipline. The primary objective is to create a comprehensive database integrating detailed soil N2O flux data and associated metadata from automated chamber-based measurements in managed systems, contributed by global data collaborators. The goal is to develop advanced AI models that enhance the predictability and interpretability of N2O emissions concerning complex covariate interactions, contributing novel insights to inform process-based models.
Designation: Postdoctoral Associate
Research Area: Soil Science, Agronomy, Data Science, Machine Learning
Location: Knoxville, TN
Eligibility/Qualification:
- Completed Ph.D. degree in soil science, agronomy, computer science, or related fields. Experience in data science applications is a plus.
- Expertise in developing and managing large, structured, scaled, and searchable MySQL databases containing multiple relational tables.
- Proficiency in using machine learning and deep learning models.
Job Description:
Postdoctoral Position in Modeling Soil Nitrous Oxide Emission Using Artificial Intelligence
The incumbent will be responsible for synthesizing a globally scaled database encompassing temporal N2O fluxes and associated metadata, creating a relational database to facilitate data-driven modeling for this project and beyond. This role involves collaboration with Michigan State University to lead database development. Additionally, the postdoc will collect and extract intermittent flux chamber data and metadata from the extensive N2O flux literature, following rigorous gas sampling strategies and drawing from databases such as USDA’s GRACEnet and the Global N Database.
To ensure compatibility among data from various sources, the postdoc will establish a standardized and scalable database structure, enabling easy querying, comparison, and integration into machine learning modeling workflows. The final database will adhere to FAIR (Findable, Accessible, Interoperable, and Re-usable) data standards and will be uploaded to a public repository with a unique identifier and rich metadata. The position requires the ability to work both independently and as part of a diverse team, overseeing daily project management and coordinating with multi-institutional collaborators to monitor progress. This is a full-time, two-year appointment contingent on funding availability and satisfactory performance, with a competitive salary and benefits package.
How to Apply:
Interested candidates should submit the following application materials:
- A cover letter detailing their qualifications and research interests.
- A current CV.
- Contact information for three professional references.
Please email your application materials as a single PDF file to [email address] with the subject line “Postdoc Application – Soil N2O Modeling.” For inquiries about the position, please contact [contact name] at [contact email].
Last Date for Apply: [Insert application deadline date]
Table: Required Qualifications
| Qualification | Requirement |
|---|---|
| Completed Ph.D. degree | Soil science, agronomy, computer science, or related fields |
| Expertise | Developing and managing large, structured, scaled, and searchable MySQL databases |
| Proficiency | Machine learning and deep learning models |
Join us 