基于LSTM和气候要素分带的金沙江上游流域径流模拟研究
张子凡(1997— ),男,河南焦作人,硕士生,主要研究方向为水循环与水资源。E-mail: zfzhang97@mail.ynu.edu.cn |
收稿日期: 2023-01-08
修回日期: 2023-03-26
网络出版日期: 2023-06-26
基金资助
国家自然科学基金项目(42171129)
国家自然科学基金项目(42201040)
第二次青藏高原综合科学考察研究项目(2019QZKK0208)
中国华电科技合作项目(CHDKJ21-02-02)
Runoff simulation of the upper Jinsha River Basin based on LSTM driven by elevation dependent climatic forcing
Received date: 2023-01-08
Revised date: 2023-03-26
Online published: 2023-06-26
Supported by
National Natural Science Foundation of China(42171129)
National Natural Science Foundation of China(42201040)
The Second Tibetan Plateau Scientific Expedition and Research Program(2019QZKK0208)
The Science and Technology Project of China Huadian Corporation(CHDKJ21-02-02)
全球气候变暖极端事件频发的背景下,近年来金沙江上游区径流变率较1990年代显著增大,出现了百年一遇的极端洪水事件,对流域水资源利用、水库调度带来了新的挑战。金沙江上游地区范围广大、观测站点稀少,基于机器学习模型进行单目标径流模拟较传统模型具有优势,但该方法在大尺度高寒山区的径流模拟研究不足。论文应用长短期记忆(long short-term memory, LSTM)神经网络模型对金沙江上游径流年内过程进行模拟,模型由高程分带提取的日降水(GPM,0.1°×0.1°)、日均气温(ERA5Land,0.1°×0.1°)及逐日积雪面积(MODIS,500 m)数据驱动,以径流观测数据为目标进行建模,同时构建集合模型,模拟流域径流并进行模型对比。模型训练期和验证期分别为2001—2014年和2015—2019年。结果显示:2种模型在预见期15 d内模型效率系数(NSE)≥0.80,且在相邻预见期NSE接近,预见期25 d和30 d的NSE均能达到0.70以上,表明2种模型在30 d预见期内的径流模拟效果良好。以高程分带数据驱动的高程信息模型,1~5 d预见期径流模拟显著优于集合模型,7~13 d预见期优势减小,15~30 d预见期二者模拟效果相当。高程信息模型对汛期径流的模拟优于集合模型,展现出其在洪水模拟方面的优势。总体而言,高程信息模型在预见期为3 d的径流模拟中精度最高,尤其对春汛及夏汛的模拟,可为金沙江中游梯级电站水库调度提供参考,但模型对极端春季洪水模拟效果仍有待提升。
张子凡 , 刘时银 , 马凯 , 张鲜鹤 , 杨延伟 , 崔福宁 . 基于LSTM和气候要素分带的金沙江上游流域径流模拟研究[J]. 地理科学进展, 2023 , 42(6) : 1139 -1152 . DOI: 10.18306/dlkxjz.2023.06.009
The upper Jinsha River has seen increased variability of stream runoff under the global warming since 1990 and extreme flood events with a 100-year recurrence period have occurred in recent years with flood peaks double or triple that of its normal annual mean flow, which has led to challenges to the utilization of water resources and reservoir operation in the basin. The upper Jinsha River Basin covers a large area but has few observation stations. Compared to the traditional models, the single objective runoff simulation based on machine learning (ML) model has shown advantages in forecasting floods, but the research on runoff prediction of ML model for large rivers originated in alpine mountains is insufficient. In this study, the long short-term memory (LSTM) neural network model was used to simulate the annual runoff process in the upper Jinsha River and the model was driven by daily precipitation, mean temperature, and snow cover area extracted from the 500 m elevation bands of GPM, ERA5-Land, and MODIS snow cover products. The model was built with the runoff observation data as the objective. An ensemble model driven by daily means of all above parameters of the whole basin was also built and compared with the LSTM model. Both models used data from 2001-2014 for training and 2015-2019 for validation. The results show that the Nash-Sutcliffe efficiency (NSE) of the two models was greater than or equal to 0.80 within 15 days lead-time, the models had similar NSE in adjacent lead-times, and the NSE decreased to about 0.70 for the lead-times of 25 and 30 days, which indicates that the runoff simulation results of the two models are reasonable at the 30 days and shorter lead-times. Better results of runoff simulation were generated by the LSTM model driven by the vertical zonation data for the 1-5 days lead-times as compared to the ensemble model. The advantage of the vertical zonation data-driven model reduced for the 7-13 days lead-time and the simulation results are equivalent for the 15-30 days lead-time. The vertical zonation data-driven model was superior to the ensemble model in simulating flood season runoff. In general, the runoff simulation accuracy of the vertical zonation data-driven model is the highest at the 3 days lead-time, especially for spring and summer floods. We conclude that the developed model driven by the elevation zonation data can provide reliable prediction of floods, which can provide a reference for the operation of the downstream cascade hydropower stations of the middle Jinsha River. However, the improvement of the ML model for extreme spring floods should still be an important direction in future research.
表1 模型输入输出因子Tab.1 Model input and output factors |
数据 模型 | 气温/℃ | 降水/mm | 积雪面积/km2 | 流量/(m3/s) |
---|---|---|---|---|
(ERA5Land) | (GPM) | (MODIS) | (石鼓站) | |
高程 信息 模型 | 气温2500 m以下 | 降水2500 m以下 | 积雪2500 m以下 | 观测流量 |
气温2500~3000 m | 降水2500~3000 m | 积雪2500~3000 m | ||
气温3001~3500 m | 降水3001~3500 m | 积雪3001~3500 m | ||
气温3501~4000 m | 降水3501~4000 m | 积雪3501~4000 m | ||
气温4001~4500 m | 降水4001~4500 m | 积雪4001~4500 m | ||
气温4501~5000 m | 降水4501~5000 m | 积雪4501~5000 m | ||
气温5001~5500 m | 降水5001~5500 m | 积雪5001~5000 m | ||
气温5500 m以上 | 降水5500 m以上 | 积雪5500 m以上 | ||
集合模型 | 流域气温 | 流域降水 | 流域积雪 |
[1] |
陈仁升, 阳勇, 韩春坛, 等. 高寒区典型下垫面水文功能小流域观测试验研究[J]. 地球科学进展, 2014, 29(4): 507-514.
[
|
[2] |
|
[3] |
汤秋鸿, 刘星才, 周园园, 等. “亚洲水塔”变化对下游水资源的连锁效应[J]. 中国科学院院刊, 2019, 34(11): 1306-1312.
[
|
[4] |
潘保田, 李吉均. 青藏高原: 全球气候变化的驱动机与放大器(Ⅲ): 青藏高原隆起对气候变化的影响[J]. 兰州大学学报, 1996, 32(1): 108-115.
[
|
[5] |
|
[6] |
肖豪, 周春辉, 尚艳丽, 等. 基于SWAT与新安江模型的闽江建阳流域径流模拟研究[J]. 水力发电, 2022, 48(10): 19-25.
[
|
[7] |
雷磊, 吴健, 万昊, 等. 基于改进降水输入模块的农田地表中尺度径流模拟[J]. 水利水电技术, 2021, 52(S1): 149-154.
[
|
[8] |
|
[9] |
伊璇, 周丰, 王心宇, 等. 基于SOM的流域分类和无资料区径流模拟[J]. 地理科学进展, 2014, 33(8): 1109-1116.
[
|
[10] |
孙赫, 苏凤阁. 雅鲁藏布江流域多源降水产品评估及其在水文模拟中的应用[J]. 地理科学进展, 2020, 39(7): 1126-1139.
[
|
[11] |
|
[12] |
张国锐, 杨传国, 卢书梅, 等. CMORPH卫星站点融合降水的沂河流域径流模拟适用性评估[J]. 水电能源科学, 2023, 41(1): 6-9.
[
|
[13] |
|
[14] |
|
[15] |
|
[16] |
赵安周, 刘宪锋, 朱秀芳, 等. 基于SWAT模型的渭河流域干旱时空分布[J]. 地理科学进展, 2015, 34(9): 1156-1166.
[
|
[17] |
|
[18] |
|
[19] |
|
[20] |
|
[21] |
李鸿雁, 刘寒冰, 苑希民, 等. 人工神经网络峰值识别理论及其在洪水预报中的应用[J]. 水利学报, 2002, 33(6): 15-20.
[
|
[22] |
|
[23] |
|
[24] |
袁晶, 张小峰. 基于遗忘因子的BP神经网络水文实时预报方法[J]. 水科学进展, 2004, 15(6): 787-792.
[
|
[25] |
|
[26] |
|
[27] |
郭俊, 周建中, 张勇传, 等. 基于改进支持向量机回归的日径流预测模型[J]. 水力发电, 2010, 36(3): 12-15.
[
|
[28] |
|
[29] |
|
[30] |
|
[31] |
张力, 王红瑞, 郭琲楠, 等. 基于时序分解与机器学习的非平稳径流序列集成模型与应用[J]. 水科学进展, 2023, 34(1): 42-52.
[
|
[32] |
|
[33] |
|
[34] |
|
[35] |
|
[36] |
任成清, 马建国, 张冲, 等. 基于LSTM神经网络与蒙特卡罗模型的辽河源头区径流预测[J]. 水电能源科学, 2021, 39(11): 40-43.
[
|
[37] |
黄克威, 王根绪, 宋春林, 等. 基于LSTM的青藏高原冻土区典型小流域径流模拟及预测[J]. 冰川冻土, 2021, 43(4): 1144-1156.
[
|
[38] |
|
[39] |
|
[40] |
|
[41] |
|
[42] |
|
[43] |
|
[44] |
胡庆芳, 曹士圯, 杨辉斌, 等. 汉江流域安康站日径流预测的LSTM模型初步研究[J]. 地理科学进展, 2020, 39(4): 636-642.
[
|
[45] |
|
[46] |
|
[47] |
|
/
〈 |
|
〉 |