Using neural networks for near-real-time aerosol retrievals from OMPS Limb Profiler measurements

Himes, Michael D.; Taha, Ghassan; Kahn, Daniel; Zhu, Tong; Kramarova, Natalya A.

doi:https://doi.org/10.5194/amt-18-2523-2025

Articles | Volume 18, issue 11

https://doi.org/10.5194/amt-18-2523-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-18-2523-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 11

Research article

|

13 Jun 2025

Research article |

| 13 Jun 2025

Using neural networks for near-real-time aerosol retrievals from OMPS Limb Profiler measurements

Michael D. Himes, Ghassan Taha, Daniel Kahn, Tong Zhu, and Natalya A. Kramarova

Data sets

Research compendium Michael D. Himes et al. https://doi.org/10.5281/zenodo.11477425

OMPS-NPP L1G LP Radiance EV Wavelength-Altitude Grid swath orbital 3slit V2.6 G. Jaross https://doi.org/10.5067/YVE3FSNJ59RQ

OMPS-NPP L2 LP Aerosol Extinction Vertical Profile swath daily 3slit V2 Ghassan Taha https://doi.org/10.5067/CX2B9NW6FI27

Model code and software

MARGE Michael D. Himes https://github.com/exosports/MARGE

Video supplement

Animation of the V2.1 and NRT average retrieved extinction coefficient between 19.5–21.5 km at 997 nm for the 2024 Ruang eruptions Michael D. Himes et al. https://doi.org/10.5281/zenodo.14623952

Short summary

The Ozone Mapping and Profiler Suite's Limb Profiler (OMPS LP) yields near-global coverage and information about how aerosols from volcanic eruptions and major wildfires is vertically distributed through the atmosphere. We developed a machine learning method to characterize aerosols using OMPS LP measurements about 60 times faster than the current approach.