Optimizing Radar-Based Rainfall Estimators Using Machine Learning Modles

Weather radar research has produced numerous radar-based rainfall estimators based on climate, rainfall intensity, a variety of ground-truthing instruments and sensors (e.g., rain gauges, disdrometers), and techniques. Although each research direction gives improvement, their collective application in an operational sense still yields uncertainty in rainfall estimation at different times. This study aims to explore the concept of implementing Machine Learning (ML) models in choosing the optimal radar-based rainfall estimator from a group of estimators at each bin of a radar scan.  

The Canadian King City C-Band radar was used with a GEONOR T-200B rain gauge, a total of 263 sample points, to establish a group of polarimetric-based rainfall estimators (R(Z), R(Z, ZDR), R(KDP)). The estimators were used to train three ML models, namely Decision Tree, Random Forest, and Gradient Boost, to choose the optimal rainfall estimators based on radar variables (Z, ZDR, KDP). Data from the Canadian Exeter C-Band radar and a Texas Electronics TE525 tipping bucket gauge at a different location were used to verify the ML models and compare their results to the classic Marshall-Gunn (1952) Z-R relation and the composite estimator produced by Bringi et al. (2011). The results show promising results for the ML models, specifically the Gradient Boost model. These encouraging results need to be further explored with more sample points to further refine the ML mod

气象雷达领域的研究已产出诸多基于气候条件、降雨强度、多种地面验证仪器与传感器（如雨量计（rain gauge）、雨滴谱仪（disdrometer））及相关技术的雷达降雨估测方法。尽管各研究方向均取得了一定进展，但在业务化场景下综合应用这些方法时，不同时段的降雨估测仍存在不确定性。本研究旨在探索利用机器学习（Machine Learning, ML）模型，从雷达扫描每个距离库（bin）对应的一组估测器中筛选最优雷达降雨估测器的思路。

本研究采用加拿大金斯顿城C波段雷达搭配GEONOR T-200B型雨量计，基于共计263个采样点，构建了一组基于偏振参数的雷达降雨估测器：R(Z)、R(Z, ZDR)、R(KDP)。利用上述估测器训练三类机器学习模型，即决策树（Decision Tree）、随机森林（Random Forest）与梯度提升树（Gradient Boost），以基于雷达变量Z、ZDR、KDP筛选最优降雨估测器。本研究采用另一站点的加拿大埃克塞特C波段雷达与Texas Electronics TE525型翻斗式雨量计采集的数据，对上述机器学习模型进行验证，并将模型结果与经典的Marshall-Gunn（1952）Z-R关系法以及Bringi等人（2011）提出的综合估测器进行对比。研究结果表明，机器学习模型展现出了良好的应用潜力，其中梯度提升树模型的表现尤为突出。本次获得的喜人结果仍需通过扩充采样点数量进一步开展研究，以优化机器学习模型性能。