Grantee Research Project Results
2024 Progress Report: A diagnostic package to facilitate and enhance chemical mechanism implementations within regional and global atmospheric chemistry models
EPA Grant Number: R840011Title: A diagnostic package to facilitate and enhance chemical mechanism implementations within regional and global atmospheric chemistry models
Investigators: Nicely, Julie M , Tong, Daniel , Follette-Cook, Melanie , Keller, Christoph
Institution: University of Maryland - College Park , Morgan State University , Universities Space Research Association
EPA Project Officer: Chung, Serena
Project Period: August 1, 2020 through May 9, 2025
Project Period Covered by this Report: August 1, 2023 through July 31,2024
Project Amount: $796,885
RFA: Chemical Mechanisms to Address New Challenges in Air Quality Modeling (2019) RFA Text | Recipients Lists
Research Category: Watersheds , Endocrine Disruptors , Environmental Engineering , Air Quality and Air Toxics , Air
Objective:
The objective of this study is to develop 1) a diagnostic software package, based on machine learning, to identify the key elements of a chemical mechanism to aid the future development of air quality models & 2) a chemical mechanism emulator that can be used as an alternative, computationally inexpensive method to simulate atmospheric chemistry.
Progress Summary:
Machine learning framework for diagnosing and emulating air quality model chemical mechanisms and application to GEOS-Chem are complete; first publication is in final stages of preparation for submission. The Python XGBoost framework emulates short- and long-term chemistry with stability and overall fidelity to capture unique events for various regimes. Surrogate models for chemistry of the planetary boundary layer vs. free troposphere and day vs. night are demonstrated to improve performance, as is implementation of a quasi-Kalman filter technique to combine predictions of chemical tendency and concentration. Prediction of PM2.5 and emulation for global model domain were added in last project year.
Future Activities:
Upon submission of our first publication, we will promptly follow up with a paper demonstrating the science applications of our software package. Development will be conducted to incorporate this GEOS-Chem emulation software within the GEOS GCM operating on a supercomputer, with the chemical prediction step specifically sent to GPUs for processing. If time allows, we will also conduct further experiments to refine chemical regime surrogate models, e.g., for biomass burning conditions, and apply the software package to CMAQ for inter-comparison.
Journal Articles:
No journal articles submitted with this report: View all 4 publications for this projectSupplemental Keywords:
atmosphere, air quality, ozone, modeling, chemical sensitivity, model performance, model intercomparison, contiguous US, machine learningRelevant Websites:
None
Progress and Final Reports:
Original AbstractThe perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.