As a key component of rainfall estimation, the understanding of raindrop size distribution (DSD) is a long-standing goal in meteorology and hydrology. Given that weather radar can observe the precipitation microphysics over large spatial and temporal scales, it has been broadly applied in DSD estimation. Traditional polynomial regression algorithms that correlate DSD parameters and radar signatures are still widely applied due to their simple structure and acceptable accuracy. This study proposes a new DSD retrieval model using dual-polarization radar observations based on long short-term memory (LSTM) network techniques. Three schemes able to retrieve the parameters of a normalized gamma DSD (LSTM-D0, LSTM-Nw, and LSTM-μ) are proposed with different combinations of polarimetric radar measurement inputs. All LSTM estimators exhibit better performance than the polynomial regression method. The Nash-Sutcliffe efficiency coefficient for estimates of drop median diameter (D0) and intercept parameter (Nw) increases from 0.93 and 0.70 to 0.95 and 0.93 respectively at Chilbolton station. Poor estimates of the shape parameter (μ) using the polynomial regression estimator complicate real applications, whereas the remarkable improvement of LSTM model estimation facilitates practical applications. The temporal and spatial predictability is then estimated to investigate long-term estimator performance for various radars, or at least for all radar pixels of a single radar. The predictability, measured by the Nash coefficient, increases temporally by 0.08, 0.31, and 0.39 and spatially by 0.03, 0.19, and 0.23 for the parameters D0, log10Nw, and μ respectively. This study contributes to improving quantitative precipitation estimates from radar polarimetry, enabling a better understanding of precipitation microphysics.

中文翻译：

---

使用神经网络从极化雷达观测中检索雨滴尺寸分布 (DSD)


作为降雨估算的关键组成部分，了解雨滴尺寸分布（DSD）是气象学和水文学的长期目标。由于天气雷达可以在大时空尺度上观测降水微物理，因此在DSD估算中得到了广泛的应用。将 DSD 参数与雷达特征相关联的传统多项式回归算法由于结构简单且精度可接受，仍然得到广泛应用。本研究提出了一种基于长短期记忆（LSTM）网络技术的双偏振雷达观测的新 DSD 检索模型。提出了三种能够检索归一化伽玛 DSD 参数的方案（LSTM-D0、LSTM-Nw 和 LSTM-μ），并采用不同的极化雷达测量输入组合。所有 LSTM 估计器都表现出比多项式回归方法更好的性能。 Chilbolton 站用于估计水滴中值直径 (D0) 和截距参数 (Nw) 的 Nash-Sutcliffe 效率系数分别从 0.93 和 0.70 增加到 0.95 和 0.93。使用多项式回归估计器对形状参数（μ）的估计较差，使实际应用变得复杂，而 LSTM 模型估计的显着改进则有利于实际应用。然后估计时间和空间可预测性，以研究各种雷达或至少单个雷达的所有雷达像素的长期估计器性能。对于参数 D0、log10Nw 和 μ，通过纳什系数测量的可预测性在时间上分别增加了 0.08、0.31 和 0.39，在空间上分别增加了 0.03、0.19 和 0.23。 这项研究有助于改进雷达偏振测量的定量降水估算，从而更好地了解降水微物理。