This presentation will highlight which model and geographical parameters can provide “predictive skill”. By skill we mean an ability to associate different behaviour in (a) and (b) with different meteorological/geographical scenarios. Model parameters used include standard model output, and newly created diagnostics that focus on addressing known limitations of a global model. Standard output includes convective rainfall fraction, mid tropospheric wind speed and clear sky solar radiation, whilst new diagnostics include a cell drift parameter, to compensate for the non-advection of convective cells, and also topographic modulation parameters. Geographical parameters we have utilised include the land fraction and the standard deviation of the sub-grid orography. Reference will also be made to flash flood case studies which have informed the investigations.
The main practical benefit of this system will be a greatly improved capacity to predict extreme point rainfall, and thereby provide early warnings, for the whole world, of flash flood potential for lead times that extend beyond day 5. This is being incorporated into the suite of products output by GLOFAS (the GLObal Flood Awareness System) which is hosted at ECMWF. As such this work offers a very cost-effective approach to satisfying user needs right around the world. This field has hitherto relied on using very expensive high-resolution ensembles; by their very nature these can only run over small regions, and only for lead times up to about 2 days.
![](images/flag.png)
![](images/blue_ribbon.png)