[1]何健,余宇峰,冯胜男,等.智能水文预报模型的研究与应用[J].江苏水利,2023,(10):1-5.
 HE Jian,YU Yufeng,FENG Shengnan,et al.Research and application of intelligent hydrological forecasting model[J].JIANGSU WATER RESOURCES,2023,(10):1-5.
点击复制

智能水文预报模型的研究与应用()
分享到:

《江苏水利》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年10期
页码:
1-5
栏目:
水文水资源
出版日期:
2023-10-15

文章信息/Info

Title:
Research and application of intelligent hydrological forecasting model
文章编号:
1007-7839(2023)10-0001-0005
作者:
何健1余宇峰2冯胜男1邓劲柏2李凯1
(1. 江苏省水文水资源勘测局,江苏 南京 210029;2. 河海大学 计算机与信息学院,江苏 南京 211110)
Author(s):
HE Jian1 YU Yufeng2 FENG Shengnan1 DENG Jinbai2 LI Kai1
(1. Jiangsu Province Hydrology and Water Resources Investigation Bureau, Nanjing 210029, China;2. College of Computer and Information, Hohai University, Nanjing 211110, China)
关键词:
水文预报记忆网络搜索算法LSTMASCS
Keywords:
hydrological prediction memory network search algorithm LSTM ASCS
分类号:
TV124
文献标志码:
B
摘要:
洪水过程具有高度非线性、复杂性和非平稳性特征。将自适应步长的布谷鸟搜索(ASCS)算法应用于神经网络水文模型参数优化中,构建ASCS-LSTM洪水预报模型,并采用注意力机制进一步提高输入输出的相关性,实现高精度的智能洪水预测。在秦淮河流域的水位预测实验表明,ASCS-LSTM预报模型的预报结果要优于传统机器学习模型,稳定性和精确度得到提升,可为水文预报提供新思路。
Abstract:
The flood process is highly nonlinear, complex and non-stationary. The ASCS-LSTM flood forecasting model is built, which adopts adaptive step size cuckoo search (ASCS) algorithm to optimize parameter of LSTM neural network hydrological model, and which applies the attention mechanism to further improve the relevance of input and output to achieve high-precision intelligent flood prediction. The water level prediction experiments in Qinhuai River basin show that ASCS-LSTM forecasting model can achieve more stable and accurate forecasting results than those of traditional machine learning model, and thus providing a new idea for hydrological forecasting.

参考文献/References:

[1]张建云. 中国水文预报技术发展的回顾与思考[J]. 水科学进展,2010,21(4):435-443.
[2]刘志雨,刘玉环,孔祥意. 中小河流洪水预报预警问题与对策及关键技术应用[J]. 河海大学学报(自然科学版),2021,49(1):1-6.
[3]张旭旻,瞿思敏,李倩,等. 基于协整理论的淮河流域上游洪水预报实时校正方法[J]. 水资源保护,2022,38(6):88-95,145.
[4]MOSAVI A,OZTURK P,CHAU K W. Flood prediction using machine learning models: literature review[J]. Water 2018(10),1536:1-40.
[5]SUN A Y,SCANLON B R. How can big data and machine learning benefit environment and water management:Asurvey of methods,applications,and future directions[J]. Environmental Research Letters,2019(1):48.
[6]SCHMIDT L,HEE F,ATTINGER S,et al. Challenges in applying machine learning models for hydrological inference:a case study for flooding events across Germany[J]. Water Resources Research,2020,56(5):1-10.
[7]芮孝芳. 水文学与“大数据”[J].水利水电科技进展,2016,36(3):1-4.
[8]张珂,牛杰帆,李曦,等. 洪水预报智能模型在中国半干 旱半湿润区的应用对比[J]. 水资源保护,2021,37(1):28-35.
[9]GHORBANI M A,ZADEH H A,ISAZADEH M,et al. A comparative study of artificial neural network (MLP,RBF) and support vector machine models for river flow prediction[J]. Environmental Earth Sciences,2016,75(6):476.
[10]冯钧,潘飞. 一种LSTM-BP多模型组合水文预报方法[J]. 计算机与现代化,2018(7):82-85.
[11]ZHANG D,LIN J,PENG Q,et al. Modelling and simulating of reservoir operation using the artificial neural network, support vector regression,deep learning algorithm[J]. Journal of Hydrology,2018,56(5):720-736.
[12]马凯凯,李士进,王继民,等. 数据驱动的中小河流智能洪水预报方法对比研究[J]. 中国科学技术大学学报,2016,46(9):774-779.
[13]Hochreiter,Sepp,Schmidhuber,et al. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[14]CUI Z,ZHOU Y,GUO S,et al. A novel hybrid XAJ-LSTM model for multi-step-ahead flood forecasting [J]. Hydrology Research,2021(3):1436-1454.
[15]周研来,郭生练,张斐章,等. 人工智能在水文预报中的应用研究[J]. 水资源研究,2019,8(1):1-12.
[16]DING Y,ZHU Y,FENG J,et al. Interpretable spatio-temporal attention LSTM model for flood forecasting[J]. Neurocomputing,2020,40(3):348-359.
[17]LI K,WAN D,ZHU Y,et al. The applicability of ASCS-LSTM-ATT model for water level prediction in small-andmedium-sized basins in China[J]. Journal of Hydroin- formatics,2020,22(6):1693-1717.

相似文献/References:

[1]左亚会,徐敏月,韩 阳.基于改进RBF网络模型的中长期水文预报[J].江苏水利,2017,(02):9.
 ZUO Yahui,XU Minyue,HAN Yang.Mid and long term hydrological forecast based on improved RBF n etwork model[J].JIANGSU WATER RESOURCES,2017,(10):9.

备注/Memo

备注/Memo:
收稿日期:2023-02-23
基金项目:江苏省水利科技项目(2021065);国家重点研发计划(2021YFB3900605)
作者简介:何健(1984—),男,高级工程师,博士,主要从事水文预报工作。E-mail:longlivehj@hotmail.com
更新日期/Last Update: 2023-10-15