code and data for machine learning emulation and observational constraint of ozone modeling uncertainty
Year: 2026
Type: article
Abstract: fm_fobs_code_default_setting.py is the example machine learning code for emulating and observationally constraining uncertainty in ozone sensitivity modeling (by chemical transport models). To install gpflow: conda create -n gpflow python=3.9 conda activate gpflow python -m pip install gpflow==2.9.1 tensorflow~=2.10.0 tensorflow-probability~=0.18.0 fig_visualization.tar.gz contains codes and data to produce figures 01 to 04 in the main text. In each sub directory (fig01, fig02, fig03 and fig04), python and R scripts for visualization are stored in the code folder.
Author: Weng, Xiang
Institution: Sun Yat-sen University
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7236494923
