Comparing and Optimizing Four Machine Learning Approaches to Radar-Based Quantitative Precipitation Estimation

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 24; p. 4713
• Main Authors: Liu, Miaomiao, Zuo, Juncheng, Tan, Jianguo, Liu, Dongwei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2024
• Subjects: Accuracy; Correlation coefficient; Correlation coefficients; Data collection; Data points; Decision trees; Deep learning; Estimates; KAN deep learning; Learning algorithms; Machine learning; machine learning method; Moisture content; multivariable; Neural networks; Observational learning; Optimization; Performance evaluation; Precipitation; Quality control; Radar; Radar systems; radar-based quantitative precipitation estimation; Rain; Rainfall; Rainfall intensity; random forest; Reflectance; Support vector machines; Water; Water content; Wavelet transforms; China
• DOI: 10.3390/rs16244713
• ISSN: 2072-4292

To improve radar-based quantitative precipitation estimation (QPE) methods, this study investigated the relationship between radar reflectivity (Z) and hourly rainfall intensity (R) using data from 289 precipitation events in Shanghai between September 2020 and March 2024. Two Z-R relationship models were compared in terms of their fitting performance: Z = 270.81 R1.09 (empirically fitted relationship) and Z = 300 R1.4 (standard relationship). The results show that the Z = 270.81 R1.09 model outperforms the Z = 300 R1.4 model in terms of fitting accuracy. Specifically, the Z = 270.81 R1.09 model more effectively captures the nonlinear relationship between radar reflectivity and rainfall intensity, with a higher degree of agreement between the fitted curve and the observed data points. This model demonstrated superior performance across all 289 precipitation events. This study evaluated the performance of four machine learning approaches while incorporating five meteorological features: specific differential phase shift (KDP), echo-top height (ET), vertical liquid water content (VIL), differential reflectivity (ZDR), and correlation coefficient (CC). Nine QPE models were constructed using these inputs. The key findings are as follows: (1) For models with a single-variable input, the KAN deep learning model outperformed Random Forest, Gradient Boosting Decision Trees, Support Vector Machines, and the traditional Z-R relationship. (2) When six features were used as inputs, the accuracy of the machine learning models improved significantly, with the KAN deep learning model outperforming other machine learning methods. Compared to using only radar reflectivity, the KAN deep learning model reduced the MRE by 20.78%, MAE by 4.07%, and RMSE by 12.74%, while increasing the coefficient of determination (R2) by 18.74%. (3) The integration of multiple meteorological features and machine learning optimization significantly enhanced QPE accuracy, with the KAN deep learning model performing best under varying meteorological conditions. This approach offers a promising method for improving radar-based QPE, particularly considering seasonal, weather system, and precipitation stage differentiation.