Grantee Research Project Results
2022 Progress Report: Machine-learned atmospheric chemical mechanisms
EPA Grant Number: R840012Title: Machine-learned atmospheric chemical mechanisms
Investigators: Tessum, Christopher , Riemer, Nicole
Institution: University of Illinois Urbana-Champaign
EPA Project Officer: Chung, Serena
Project Period: August 1, 2020 through July 31, 2023 (Extended to July 31, 2024)
Project Period Covered by this Report: August 1, 2021 through July 31,2022
Project Amount: $399,469
RFA: Chemical Mechanisms to Address New Challenges in Air Quality Modeling (2019) RFA Text | Recipients Lists
Research Category: Air , Air Quality and Air Toxics , Early Career Awards
Objective:
The objective of the work proposed here is to produce a machine-learned condensed chemical mechanism that provides accurate results in air quality modeling simulations under a wide variety of atmospheric conditions. The proposed work builds on preliminary studies where we have created a neural-network-based chemical mechanism that operates with fewer chemical species and orders-ofmagnitude less computational cost than the reference mechanism it was trained on, while reproducing diurnal cycles with low error in 90% of randomly initialized simulations. The proposed project will focus on reducing error in the remaining 10% of cases.
Progress Summary:
We have coupled the near-explicit gas-phase Master Chemical Mechanism (MCM) with the state-of-art Particle-resolved Monte Carlo Model for Simulation Aerosol Interactions and Chemistry (PartMC-MOSAIC). The combined multiphase chemical mechanism is a detailed reference for emulation, and we have created datasets for training and testing.
We have created an optimized autoencoder to reduce the dimensionality of our datasets and a Neural ODE model to create multi-phase chemistry surrogate model. The surrogate model is designed to predict the derivative of concentration which is integrated forward in time by an implicit ODE solver. This Neural ODE framework is able to overfit on a relatively small training dataset, and we are currently working to increase its capability of generalization by increasing the amount of data it is trained on.
Future Activities:
In the subsequent reporting period, we plan to finish Task 2: Train and test neural network, and also Task 3: implementing the neural network in a chemical transport model.
Journal Articles on this Report : 1 Displayed | Download in RIS Format
| Other project views: | All 15 publications | 2 publications in selected types | All 2 journal articles |
|---|
| Type | Citation | ||
|---|---|---|---|
|
|
Kelp MM, Jacob DJ, Kutz JN, Marshall JD, Tessum CW. Toward stable, general machine-learned models of the atmospheric chemical system. Journal of Geophysical Research-Atmospheres 2020;125:e2020JD032759. |
R840012 (2021) R840012 (2022) R840012 (2023) R840012 (Final) R835873 (2020) R835873 (Final) R840014 (2023) R840014 (Final) |
Exit Exit |
Supplemental Keywords:
machine learning, neural network, MOSAIC, PartMC, MCM, ambient air, modelingRelevant Websites:
Machine-learned atmospheric chemical mechanisms Exit
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.