[1]陈剑飞,李勇,刘俊江,等.耦合陆面水文模型和机器学习方法的水库径流量预报及应用[J].气象研究与应用,2022,43(01):1-7.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.01]
　Chen Jianfei,Li Yong,Liu Junjiang,et al.Yantan Reservoir runoff forecast and application coupled with land surface hydrological model and machine learning method[J].Journal of Meteorological Research and Application,2022,43(01):1-7.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.01]
点击复制

耦合陆面水文模型和机器学习方法的水库径流量预报及应用()
分享到：

气象研究与应用[ISSN:1673-8411/CN:45-1356/P]

卷:
第43卷
期数:
2022年01期
页码:
1-7
栏目:
研究论文
出版日期:
2022-03-25

文章信息/Info

Title:
Yantan Reservoir runoff forecast and application coupled with land surface hydrological model and machine learning method
作者:
陈剑飞1;  李勇1;  刘俊江2;  钟利华1;  史彩霞1;  袁星2; 3;  钟华昌4
1. 广西壮族自治区气象灾害防御技术中心, 南宁 530022;
2. 南京信息工程大学水文与水资源工程学院, 南京 210044;
3. 中国科学院东亚区域气候-环境重点实验室, 北京 100029;
4. 广西桂冠电力股份有限公司, 南宁 530029
Author(s):
Chen Jianfei1;  Li Yong1;  Liu Junjiang2;  Zhong Lihua1;  Shi Caixia1;  Yuan Xing2; 3;  Zhong Huachang4
1. Guangxi Meteorological Disaster Prevention Center, Nanning 530022, China;
2. School of Hydrology and Water Resources, Nanjing University of Information Science and Technology, Nanjing 210044, China;
3. Key Laboratory of Regional Climate-Environment for Temperate East Asia, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029;
4. Guangxi Guiguan Electric Power Co., Ltd., Nanning 530029, China
关键词:
耦合; 陆面水文模型; 机器学习; 径流量预报; 物理模型; 人工智能
Keywords:
coupling; land surface hydrological model; machine learning; runoff forecast; physical model; artificial intelligence
分类号:
P338
DOI:
10.19849/j.cnki.CN45-1356/P.2022.1.01
摘要:
采用智能网格预报等多种气象预报数据与陆面水文模型及机器学习方法进行耦合,以岩滩水库流域区间为例,将区间预报径流量与历史径流量数据输入长短期记忆网络模型(LSTM)进行水库入库径流量预报,通过对日径流量模拟试验和业务试用分析,探明该方法在短期水文预报中的适用性。结果表明,耦合气象-水文-机器学习的径流量预报模型在率定期和验证期纳什效率系数(NSE)在0.65左右,在强降水过程训练试验中,日径流量和洪峰预报合格率≥87.5%,达到甲级预报精度标准;在业务试用中,24h、48h、72h日径流量预报合格率分别为87.3%、70.4%、75.5%,达到甲级或乙级预报精度标准,满足发布正式预报的精度要求;3次较大降水过程径流量和峰现时间预报合格率均为100%,达到甲级预报精度标准;峰值预报为66.7%,达到丙级预报标准,可用于参考性预报。将物理模型与人工智能方法进行有机耦合,可提高水文预报产品精度和适用性。
Abstract:
Using a variety of meteorological forecast data such as intelligent grid forecasting to couple with land surface hydrological models and machine learning methods,taking the Yantan Reservoir watershed as an example,the interval forecast runoff and historical runoff data were input into the long-term and short-term memory network model (LSTM) to forecast the inflow runoff of the reservoir.The applicability of this method in short-term hydrological forecasting was proved through the simulation test of daily runoff and the analysis of operational trial.The results show that the Nash efficiency coefficient (NSE) of the runoff prediction model coupled with meteorology-hydrology-machine learning is about 0.65 in the calibration period and verification period.In the training test of heavy rainfall process,the qualified rate of daily runoff and flood peak prediction is greater than or equal to 87.5%,reaching the standard of A-level forecast accuracy.In the operational trial,the qualified rates of 24h,48h,and 72h daily runoff forecasts are 87.3%,70.4%,and 75.5%,respectively,reaching the A or B level forecast accuracy standards and meeting the accuracy requirements for issuing official forecasts.The qualified rate of runoff and peak present time forecasts for the three major precipitation processes are all 100%,reaching the A-level forecast accuracy standard.The peak forecast is 66.7%,which meets the C-level forecast standard and can be used for reference forecasting.The organic coupling of physical models and artificial intelligence methods can improve the accuracy and applicability of hydrological forecast products.

参考文献/References:

[1] 韦润新,林芳.岩滩水电站水文预报方案研究[J].企业科技与发展,2011,312(18):60-61,73.
[2] 黄彩珍.岩滩水库水文预报技术分析[J].企业科技与发展,2014,385(21):34-36
[3] 包红军,王莉莉,沈学顺,等.气象水文耦合的洪水预报研究进展[J].气象,2016,42(9):1045-1057.
[4] 崔春光,彭涛,沈铁元,等.定量降水预报与水文模型耦合的中小流域汛期洪水预报试验[J].气象,2010,36(12):56-61.
[5] 曾鹏,钟利华,郑凤琴,等.基于智能网格降水产品的降尺度释用技术研究[J].气象研究与应用,2021,42(1):74-79.
[6] 彭筱,陈晓燕,黄武斌.2016年夏季不同分辨率GRAPES_MESO模式的西北地区预报效果检验[J].气象研究与应用,2019,40(4):6-11.
[7] 卢小凤,李仲怡,陈剑飞,等.智能网格产品在西江流域面雨量预报中的应用检验[J].气象研究与应用,2020,41(2):45-49.
[8] 史彩霞,郑凤琴,曾鹏,等.智能网格预报在重大活动气象服务保障中的应用——以环广西公路自行车世界巡回赛为例[J].气象研究与应用,2020,41(1):61-64.
[9] 郭玉雪,许月萍,陈浩,等.基于多种递归神经网络的海岛水库径流预报[J].水力发电学报,2021,40(9):14-26.
[10] 殷兆凯,廖卫红,王若佳,等.基于长短时记忆神经网络(LSTM)的降雨径流模拟及预报[J].南水北调与水利科技, 2019, 17(6):1-9,27.
[11] 梁振清,陈生.基于深度学习和雷达观测的华南短临预报精度评估[J].气象研究与应用,2020,41(1):41-47.
[12] Liu J,Yuan X, Zeng J H,et al.Ensemble Streamflow Forecasting over a Cascade Reservoir Catchment with Integrated Hydrometeorological Modeling and Machine Learning[J].Hydrology and Earth System Science,2022(26):265-278.
[13] Dai Y J,Dickinson R,Wang Y P.A Two-Big-Leaf Model for Canopy Temperature,Pphotosynthesis,and Stomatal Conductance[J]. Journal and Climate, 2004,17(12):2281-2299.
[14] Dai Y,Zeng X,Dickinson R.The Common Land Model[J].Bull. Am. Meteorol. Soc., 2003, 84(8):1013-1024.
[15] Yuan X, Ma F,Wang L,et al. An Experimental Seasonal Hydrological Forecasting System over the Yellow River Basin-Part 1:Understanding the Role of Initial Hydrological Conditions[J]. Hydrology and Earth System Science, 2016,20(6):2437-2451.
[16] Yuan X,Ji P,Wang L,et al. High-Resolution Land Surface Modeling of Hydrological Changes over the Sanjiangyuan Region in the Eastern Tibetan Plateau:1. Model Development and Evaluation[J]. Journal of Advances in Modeling Earth Systems,2018(10):2806-2828.
[17] Duan Q Y,Sorooshian S,Gupta V K. Optimal Use of SCEUA Global Optimization Method for Calibrating Watershed Models[J].Journal of Hydroogyl,1994(158):265-284.
[18] Getirana A C V,Boone A,Yamazaki D,et al.The Hydrological Modeling and Analysis Platform (HyMAP):Evaluation in the Amazon Basin[J]. Journal of Hydrometeorology,2012(13):1641-1665.
[19] Luo X,Li H Y,Leung L R,et al.Modeling Surface Water Dynamics in the Amazon Basin Using Mosart-Inundation V1.0:Impacts of Geomorphological Parameters and River Flow Representation[J].Geoscientific Model Development Discussions,2017,10(3):1-42.
[20] 中华人民共和国国家质量监督检验检疫总局,中国国家标准化管理委员会.水文情报预报规范:GB/T22482-2008[S].北京:中国标准出版社,2008.

备注/Memo

备注/Memo:
收稿日期:2022-01-28。
基金项目:国家自然科学基金项目(41861124005)、国家重点研发计划"全球变化及应对"专项课题(2018YFA0606002)
作者简介:陈剑飞(1975-),男,高工,主要从事专业气象技术服务及管理工作。E-mail:497933494@qq.com
通讯作者:钟利华(1962-),女,正研级高工,主要从事专业气象预报服务工作。E-mail:1427962612@qq.com
更新日期/Last Update: 1900-01-01