README

Luke Conibear, Carly L. Reddington, Ben J. Silver, Ying Chen, Christoph Knote, Stephen R. Arnold, Dominick V. Spracklen (2021): Supplementary Data: Machine Learning Emulation of Long−Term Air Pollution Exposure and Disease Burden from Emission Changes in China. [Dataset]. https://doi.org/10.5518/1055

Files within "emulators.zip":
- One folder for each of the outputs:
  - Ambient fine particule matter (PM2.5, annual−mean) concentrations. Denoted by PM2_5_DRY.
  - Ozone (O3, maximum 6−monthly−mean daily−maximum 8−hour) concentrations. Denoted by o3_6mDM8h.
- Within each folder, each emulator is within files named: "emulator_<OUTPUT>_<LATITUDE>_<LONGITUDE>.joblib"
- <OUTPUT> is PM2_5_DRY for PM2.5, and o3_6mDM8h for O3.
- <LATITUDE> and <LONGITUDE> are replaced with the location for that emulator e.g. 35.25 and 95.25 (always 2 decimal places).
- There is 1 emulator per grid in China (15,278 grid cells in total).
- The code (Python) to use these emulators is available through: 
  - Conibear L 2021 lukeconibear/emulator_annual: Long-term emulator of WRFChem (Version v1.0.0). Zenodo. https://doi.org/10.5281/zenodo.5549368