A support vector machine-based method for improving real-time hourly precipitation forecast in Japan
A support vector machine-based method for improving real-time hourly precipitation forecast in Japan
复制标题
DOI：
10.1016/j.jhydrol.2022.128125
复制
发表时间：
2022-09
影响因子：
6.4
通讯作者：
Gaohong Yin;T. Yoshikane;Kosuke Yamamoto;T. Kubota;K. Yoshimura
中科院分区：
文献类型：
--
作者：
Gaohong Yin;T. Yoshikane;Kosuke Yamamoto;T. Kubota;K. Yoshimura
实时降水预报有助于水资源管理和与水有关的灾害预警。然而，数值天气预报（NWP）模式提供的降水预报偏差。本研究提出将联合收割机支持向量机（SVM）回归与基于分位数的偏差校正方法相结合，以改善日本39小时降水的实时预报。五种方法进行了比较和评估，这包括SVM回归，分位数映射（QM），累积分布函数变换（CDFt），和SVM和QM（或CDFt）的组合。结果表明，SVM和CDFt的组合（即，SVM-CDFt）通常提供最高的精度和良好的计算效率。在交叉验证实验中，SVM单独改善了小时降水量的空间表示，相关系数从1月份的0.387增加到0.490，从0.235增加到7月份的0.296。然而，SVM低估了小时降水和强降水事件的变化。QM和CDFt在修正模拟降水偏差方面表现良好，但在修正雨带位置方面能力有限。结合SVM和基于分位数的方法利用这两种方法，提供了一个更一致的变化与观测和更好地预测极端降水事件，虽然高估的降雨面积见证。该方法概念简单，计算效率高，预报精度明显提高，特别是SVM-CDFt方法，有利于实时降水预报和洪水预警。
Real-time precipitation forecast facilitates water management and water-associated disaster early warning. However, numerical weather prediction (NWP) models provide precipitation forecasts with bias. This study proposed to combine support vector machine (SVM) regression with quantile-based bias correction method to improve real-time 39-hour precipitation forecasts in Japan. Five methods were compared and evaluated against observations, which include SVM regression, quantile mapping (QM), cumulative distribution function transform (CDFt), and the combination of SVM and QM (or CDFt). Results indicated that the combination of SVM and CDFt (i.e., SVM-CDFt) generally provided the highest accuracy with good computational efficiency. SVM alone improved the spatial representation of hourly precipitation with a correlation coefficient increased from 0.387 to 0.490 in January and from 0.235 to 0.296 in July in the cross-validation experiment. However, SVM underestimated the variability of hourly precipitation and heavy precipitation events. QM and CDFt perform well in correcting the bias in modeled precipitation, while they have limited capability in correcting the rainband location. Combining SVM and quantile-based method took advantage of both approaches, providing a more consistent variability with observations and better predicted extreme precipitation events, although overestimation of rainfall area was witnessed. The simple concept, high computational efficiency, as well as evident improvement in forecast accuracy make the combined cases, especially the SVM-CDFt method, beneficial for real-time precipitation forecast and flood early warning.