LassoCMAQ
Home
What Is LassoCMAQ
- LassoCMAQ is a computationally efficient reduced-form CMAQ model, developed using the least absolute shrinkage and selection operator (LASSO) together with an adaptive logit transformation of the response variable.
- It estimates ozone and PM2.5 concentrations from regional emission-control scenarios in about 30 seconds per scenario. The model computes concentrations for every grid cell at every hour, enabling rapid what-if exploration without running CMAQ.
How to Use LassoCMAQ
- Enter a 17 × 7 emission scenario matrix (Region × Emission Sector) specifying emission change ratios (e.g., 0.9 = 10% reduction from the baseline).
- Select pollutant(s) and click Run to estimate CMAQ-equivalent concentrations for the selected scenario.
- Inspect maps and summary metrics; click a grid cell to view the top five influential variables for the corresponding region.
- Download the scenario inputs and the full model results as needed.
Citation
D.-B. Lee et al., A LASSO-based reduced-form CMAQ model for predicting ozone and PM2.5 responses to emission changes in South Korea (submitted)
Control Scenario
How to Set an Emission Scenario
- Use the emission scenario matrix to define emission change ratios. Each cell represents an emission change ratio (Region × Emission Sector).
- Edit cells directly.
- Update all cells at once.
- Update a row or column at once.
- Upload an emission scenario file.
© Soongsil University Machine Learning Lab All Rights Reserved.