We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Polarimetric Retrieval of Raindrop Size Distribution: Double‐Moment Normalization Approach and Machine Learning Techniques.
- Authors
Shin, Kyuhee; Kim, Kwonil; Song, Joon Jin; Lee, GyuWon
- Abstract
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 measurementThe retrieval is based on the double‐moment normalization for potential universal applicationsThe suggested model was applied to the X‐band polarimetric radar data and outperformed the conventional polynomial regression model
- Subjects
RAINDROP size; MACHINE learning; MATHEMATICAL forms; RANDOM forest algorithms; MICROPHYSICS; RADAR meteorology
- Publication
Geophysical Research Letters, 2024, Vol 51, Issue 1, p1
- ISSN
0094-8276
- Publication type
Article
- DOI
10.1029/2023GL106057