Results show that FIRA workflow introduces an increasing trend in RMSE from 250 MW to over 500 MW along with the forecast period, and consistently underestimates FRP values by about 200 MW (Figure 6a‐1 ).
← all excerpts
Fire Intensity and spRead forecAst (FIRA): A Machine Learning Based Fire Spread Prediction Model for Air Quality Forecasting Application.
2
—
—
The sentences
● The timeseries of UFS‐Smoke surface smoke concentration at a given site should have a positive trend.