Grantee Research Project Results
2021 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
Current Investigators: Nicely, Julie M , Keller, Christoph , Follette-Cook, Melanie , Tong, Daniel , Ivatt, Peter
Institution: University of Maryland - College Park , Morgan State University , Universities Space Research Association
EPA Project Officer: Chung, Serena
Project Period: August 1, 2020 through July 31, 2023 (Extended to July 31, 2025)
Project Period Covered by this Report: August 1, 2020 through July 31,2021
Project Amount: $796,885
RFA: Chemical Mechanisms to Address New Challenges in Air Quality Modeling (2019) RFA Text | Recipients Lists
Research Category: Air , Air Quality and Air Toxics
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 (AQMs) and 2) a chemical mechanism emulator that can be used as an alternative, computationally inexpensive method to simulate atmospheric chemistry.
Progress Summary:
Development of a user-friendly machine learning framework for diagnosing and emulating air quality model chemical mechanisms is underway. Based in Python XGBoost and leveraging Dask to optimize parallel computational workflow, the framework currently includes automation for k-fold crossvalidation,
parallelization for parsing and training on large model data sets, adaptability for different compute environment scenarios, and report-out diagnostics that visualize SHAP (SHAapley Additive exPlanatios) values.
Future Activities:
Development of the software package will continue, with testing against diverse air quality model use cases and solicitation of prospective new features from the user community. The prototype software framework will be demonstrated on the GEOS-Chem and CMAQ air quality models by generating diagnostics aimed at highlighting key differences in the two models’ chemical mechanisms. In the next project year, we also anticipate undertaking initial methodological development for the embedding of machine learning-based chemical mechanism surrogates into a parent air quality model.
Journal Articles:
No journal articles submitted with this report: View all 2 publications for this projectSupplemental Keywords:
atmosphere, air quality, ozone, modeling, chemical sensitivity, model performance, model intercomparison, contiguous US, machine learningProgress 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.