Details

Autor(en) / Beteiligte

• Shin, Kyuhee
• Kim, Kwonil
• Song, Joon Jin
• Lee, GyuWon

Titel

Polarimetric Retrieval of Raindrop Size Distribution: Double‐Moment Normalization Approach and Machine Learning Techniques

Ist Teil von

• Geophysical research letters, 2024-01, Vol.51 (1), p.n/a

Ort / Verlag

Washington: John Wiley & Sons, Inc

Erscheinungsjahr

2024

Quelle

Electronic Journals Library

Beschreibungen/Notizen

• Retrieving raindrop size distribution (DSD) is essential to understanding precipitation processes. Conventional approaches based on polarimetric radar (e.g., polynomial regression) struggle to accurately capture the inherent nonlinearity between DSD parameters and radar measurables. In contrast, machine learning (ML) algorithms offer a promising solution as it effectively models the complex non‐linear relationship. We have developed an ML algorithm to retrieve DSD parameters using polarimetric radar variables in a framework of double‐moment normalization. The potentially stable and invariant double‐moment normalized DSD enables the applicability of the algorithm in any climatic regime or any precipitation system. To improve the robustness of the model to measurement noises, we employed training samples with random noise. All ML algorithms outperformed the conventional method, with the random forest being the best model. This study highlights the effectiveness of the developed algorithm as a tool for understanding the DSD characteristics from polarimetric radar measurements. Plain Language Summary Raindrop size distribution (DSD) is an essential component of precipitation characteristics. DSD is often represented by a particular mathematical functional form which is composed of a few parameters. Retrieving the parameters from radar measurements can assist in identifying the microphysics of precipitation systems at high spatiotemporal resolution. This study developed a machine learning algorithm to retrieve parameters of double‐moment normalized DSD, which offers advantages over the other DSD forms thanks to two characteristic parameters and potentially universal normalized DSD shape. This study also demonstrates the practical application of the trained model by retrieving DSD information from real radar measurements. Key Points We present a machine learning algorithm for the retrieval of raindrop size distribution parameters based on polarimetric radar measurement The retrieval is based on the double‐moment normalization for potential universal applications The suggested model was applied to the X‐band polarimetric radar data and outperformed the conventional polynomial regression model