Title: Improve Cloud Modeled by WRF using COSP and Generative Adversarial Network
Institution(s) Represented: Texas A&M University - Zheng Lu
Lead PI: Zheng Lu
AQRP Project Manager: Elena McDonald-Buller
TCEQ Project Liaison: Bright Dornblaser
Awarded Amount: $98,427.00
Abstract
The cloud fields modeled by meso-scale models play an important role in the application of predicting local air quality. The cloud fields can strongly affect the formation, transportation, as well as deposition of many gaseous and particulate species, through regulating radiative transfer, influencing aqueous chemistry, and altering precipitation. However, it is very challenging to accurate predict the microphysical and macrophysical properties of cloud fields.
In this proposal, we plan to run WRF model with Texas in the center of model domain. Modeled cloud fields are feed into Cloud Feedback Intercomparison Project (CFMIP) Observation Simulator Package (COSP), so that modeled cloud can be directly compared to satellite observations. The objective is to select optimal combination of initiation state (the selection of reanalysis data) and physical packages (namely microphysics, cumulus parameterization, planetary boundary layer scheme) for the cloud simulation.
With modeled and observed cloud fields, we train a GAN (Generative Adversarial Network), a type of deep learning technique. We will perform super-resolution and image-to-image translation applications to modeled cloud microphysical fields over Texas, so that they can gain much detailed fine features, and become more accurate compared to observed cloud fields. Improved cloud fields will undoubtedly improve Texas air quality prediction.
Work Plan: projectinfoFY20_21\20-026\20-026 Scope.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Sep 2020.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Oct 2020.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Nov 2020.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Dec 2020.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Jan 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Feb 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Mar 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Apr 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR May 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Jun 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Jul 2021.pdf
Technical Report(s): projectinfoFY20_21\20-026\20-026 MTR Aug 2021.pdf
QAPP: projectinfoFY20_21\20-026\20-026 QAPP.pdf
Final Report: projectinfoFY20_21\20-026\20-026 Final Report.pdf
