Advecting Superspecies: Efficiently Modeling Transport of Organic Aerosol With a Mass‐Conserving Dimensionality Reduction Method

Abstract

The chemical transport model LOTOS‐EUROS uses a volatility basis set (VBS) approach to represent the formation of secondary organic aerosol (SOA) in the atmosphere. Inclusion of the VBS approximately doubles the dimensionality of LOTOS‐EUROS and slows computation of the advection operator by a factor of two. This complexity limits SOA representation in operational forecasts. We develop a mass‐conserving dimensionality reduction method based on matrix factorization to find latent patterns in the VBS tracers that correspond to a smaller set of superspecies. Tracers are reversibly compressed to superspecies before transport, and the superspecies are subsequently decompressed to tracers for process‐based SOA modeling. This physically interpretable data‐driven method conserves the total concentration and phase of the tracers throughout the process. The superspecies approach is implemented in LOTOS‐EUROS and found to accelerate the advection operator by a factor of 1.5–1.8. Concentrations remain numerically stable over model simulation times of 2 weeks, including simulations at higher spatial resolutions than the data‐driven models were trained on. The reversible compression of VBS tracers enables detailed, process‐based SOA representation in LOTOS‐EUROS operational forecasts in a computationally efficient manner. Beyond this case study, the physically consistent data‐driven approach developed in this work enforces conservation laws that are essential to other Earth system modeling applications, and generalizes to other processes where computational benefit can be gained from a two‐way mapping between detailed process variables and their representation in a reduced‐dimensional space.

Overview of ICARUS─A Curated, Open Access, Online Repository for Atmospheric Simulation Chamber Data

“…Data mining and model development activities related to machine learning − will benefit from the increasing availability of high-quality data as provided by ICARUS. In particular, machine learning algorithms gain more information each time there is a new “phase change” or time discontinuity with distinct characteristics that can be observed to effect a measurable system impact .…”

Improving BC Mixing State and CCN Activity Representation With Machine Learning in the Community Atmosphere Model Version 6 (CAM6)

“…Therefore, given the dilemma of the need for particle-resolved properties and consideration of computational efficiency, machine learning (ML) techniques can provide a new approach for integrating particle-resolved models and large-scale GCMs. The use of machine learning in atmospheric sciences has been a new but fast-developing field, with recent applications in many areas, such as atmospheric chemistry (e.g., Kelp et al, 2020;Kelp et al, 2022;Sturm et al, 2023;Sturm & Wexler, 2020), aerosol microphysics (e.g., Yu et al, 2022), air quality (e.g., Ruan et al, 2023;Zheng et al, 2023), and remote-sensing (e.g., Grange et al, 2018). Some recent studies have attempted to apply machine learning to diagnose aerosol mixing states in GCMs.…”

Implementation of a Parallel Reduction Algorithm in the Generator of Reduced Organic Aerosol Mechanisms (Genoa V2.0): Application to Multiple Monoterpene Aerosol Precursors

“…Notable examples include the Common Representative Intermediates (CRI) mechanisms Weber et al, 2020) and recently AMORE mechanism (Wiser et al, 2023). Additionally, emerging data-driven approaches have been developed to enhance the computational efficiency of key processes involved in 3-D CTM modeling, including chemical integration (Kelp, Jacob, Lin, & Sulprizio, 2022;Shen et al, 2022) and transport (Sturm et al, 2023).…”