CLDAS降水产品的适用性分析及机器学习订正应用

Abstract
Figure/Table
References
Related Citation (1)

Download: HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In order to obtain the refined evaluation conclusion of the multi-source precipitation fusion real-time analysis product of the China Meteorological Administration Land Data Assimilation System(CLDAS) in Gansu Province and improve the accuracy of the product,precipitation data from 2 215 ground stations in Gansu Province were used as the test source to evaluate the applicability of CLDAS rapid fusion and real-time fusion precipitation products.Based on the evaluation conclusion,machine learning methods and optimization strategies were used to correct the CLDAS precipitation product.The results showed that the CLDAS precipitation product can better reflect the spatiotemporal distribution of precipitation in Gansu Province.The accuracy of daily values is not as good as hourly values.The XGBoost algorithm has significant advantages over other models,and its correction effect is more significant when precipitation is high.By improving the quality of the training dataset,feature engineering,and fine-tuning optimization,the XGBoost model reduces the root mean square error of precipitation above level 3 by nearly 50%,significantly improves the misjudgment of precipitation between level 1 and level 2.This model and algorithm can be applied to fields with the same climate characteristics.

Key words： CLDAS precipitation product assessment machine learning XGBoost model

Received: 23 April 2023

ZTFLH:

P426.6

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wang Yaping
	Wang Suichan
	Kong Lingwang

Cite this article:

Wang Yaping,Wang Suichan,Kong Lingwang. Applicability analysis and machine learning correction of CLDAS precipitation product[J]. Meteorological Hydrological and Marine Instrument, 2024, 41(3): 111-115.

URL:

http://www.qxswhy.com/EN/ OR http://www.qxswhy.com/EN/Y2024/V41/I3/111

[1]	师春香,潘旸,谷军霞,等.多源气象数据融合格点实况产品研制进展[J].气象学报,2019,77(4):774-783.
[2]	崔园园,张强,覃军,等.CLDAS 融合土壤湿度产品在东北地区的适用性评估及订正[J].中国农业气象,2019,40(10):660-668.
[3]	蒋雨荷,黄晓龙,李诗颖,等.四川CLDAS 5km小时能见度实况产品与能见度观测站资料质量对比评估[J].高原山地气象研究,2020,40(3):73-78.
[4]	刘佩佩,宋海清,鲍炜炜,等.CLDAS和GLDAS土壤温度数据在陕西省的适用性评估[J].气象科技,2021,49(4):604-611.
[5]	李师颖,吴薇,黄晓龙.四川省CLDAS和ECMWF再分析数据风速产品评估[J].高原山地气象研究,2020,40(4):70-76.
[6]	董春卿,郭媛媛,张磊,等.基于CLDAS的格点温度预报偏差订正方法[J].干旱气象,2021,39(5):847-856.
[7]	齐铎,刘松涛,张天华,等.基于格点的中国东北中北部2 m温度数值预报检验及偏差订正[J].干旱气象,2020,38(1):81-88.
[8]	孙小龙,宋海清,李平,等.基于CLDAS资料的内蒙古干旱监测分析[J].气象,2015,41(10):1245-1252.
[9]	粟运,师春香,毛文书,等.基于CLDAS-Prcp多源融合降水产品的WRF-Hydro模式在綦江流域的水文效用[J].高原气象,2022,41(3):617-629.
[10]	贾利芳,何正梅,宋方超,等.CLDAS土壤湿度产品适用性评估[J].农业灾害研究,2022,12(1):93-95.
[11]	刘莹,师春香,王海军,等.CLDAS气温数据在中国区域的适用性评估[J].大气科学学报,2021,44(4):540-548.
[12]	崔园园,张强,李威,等.CLDAS 融合土壤相对湿度产品适用性评估及在气象干旱监测中的应用[J].海洋气象学报,2020,40(4):105-113.
[13]	苏翔,袁慧玲.集合预报统计学后处理技术研究进展[J].气象科技,2020,10(2):30-41.
[14]	李蓉,刘新伟,魏栋,等.基于区域自动站数据的兰州地区降水精细化特征[J].干旱气象,2022,40(1):55-61.
[15]	王雅琦,冯娟,李建平,等.西北地区东部夏季降水年际变化特征及其与环流的关系[J].高原气象,2020,39(2):290-300.