Regresar

Exploring a machine learning model as radar rainfall retrieval of the highest X-band radar in the world.

Abstract:

Quantitative precipitation estimation (QPE) from weather radar data is crucial for hydrological applications, which benefit of the high spatio-temporal resolution of X-band radar imagery. Nonetheless, radar rainfall retrieval process involves a challenging correction of reflectivity, which is particularly difficult for single polarized technology. In addition, high mountain topography as the Andean cordillera deeply increases the complexity of radar QPE. This study explores a Random Forest (RF), state-of-the-art data-driven model, for optimizing the radar rainfall derivation of the highest X-band radar in the world (4450 m asl) by means of single Plan Position Indicator (PPI) scans. Several features were derived from raw reflectivity to account for the evolution of rainfall along the beam. Performance of the RF model was evaluated in comparison with the well-known step-wise approach. For this, the Marshall-Palmer and a site …