首页|基于CEEMDAN-LightGBM模型的洪水预测研究

基于CEEMDAN-LightGBM模型的洪水预测研究

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
为了应对暴雨可能引发的洪涝灾害风险,基于黄河利津水文站监测的水文等数据,以LightGBM为基准模型,运用经自适应噪声完备集合经验模态分解(CEEMDAN)算法优化后的CEEMDAN-LightGBM模型对水位进行预测,并将其与长短期记忆网络(LSTM)模型、LightGBM模型的预测效果进行对比.以 2 个气候条件不同的黄河水文站(利津、花园口)的水文数据为原始数据集输入CEEMDAN-LightGBM模型,验证模型的适应性和稳定性.结果表明:CEEMDAN-LightGBM模型在水位预测方面表现出优越的性能,相较于LSTM、LightGBM模型,该模型的EMA分别减小了 46.08%、9.95%,ERMS分别减小了 33.01%、43.01%,EMAP分别减小了94.99%、3.82%,R2分别增大了 30.48%、7.58%.CEEMDAN-LightGBM模型还能预测流量这一重要水文特征,为模型预测洪水发生提供更有力的判断依据.对比CEEMDAN-LightGBM模型预测花园口水文站与利津水文站的水位和流量效果,除预测两站水位的EMAP值相差 23.64%外,EMA值、EMAP和ERMS值相差均不超过 10%,R2相差不超过 2%.
Research on Flood Prediction Based on CEEMDAN-LightGBM Model
In order to deal with the risk of flood disaster caused by rainstorm,based on hydrological data monitored by Lijin Hydrological Sta-tion on the Yellow River,the LightGBM model was taken as the benchmark model,the CEEMDAN-LightGBM model optimized by the Com-plete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)algorithm was used to predict water levels,and compared its prediction performance with the Long Short-Term Memory(LSTM)model and LightGBM model.The hydrological data from two Yellow River hydrological stations(Lijin and Huayuankou)with different climatic conditions were input into the CEEMDAN-LightGBM model as original dataset to verify the adaptability and stability of the model.The results show that the CEEMDAN-LightGBM model exhibits superior performance in water level prediction.Comparing with the LSTM and LightGBM models,the model's EMA decrease by 46.08%and 9.95%,ERMS decrease by 33.01%and 43.01%,EMAP decrease by 94.99%and 3.82%,and R2 increase by 30.48%and 7.58%,respectively.The CEEMDAN-LightGBM model can also predict the important hydrological feature of flow,providing stronger judgment basis for the model to predict flood occurrence.Comparing with the CEEMDAN-LightGBM model for predicting the water level and flow of Huayuankou hydrological station and Lijin hydrological station,except for the predicted difference of 23.64%in EMAP values between the two stations'water levels,the difference between EMAP values and ERMS values does not exceed 10%,and the difference in R2 does not exceed 2%.

flood predictionLightGBM modelCEEMDAN algorithmCEEMDAN-LightGBM modelLSTM modelLijin Hydrological Sta-tionHuayuankou Hydrological Station

王军、张宇航、崔云烨、李怡豪、吕鹏祥

展开 >

郑州航空管理学院 大数据科学研究院,河南 郑州 450015

河南日报社,河南 郑州 450014

洪水预测 LightGBM模型 CEEMDAN算法 CEEMDAN-LightGBM模型 LSTM模型 利津水文站 花园口水文站

河南省科技攻关计划河南科技智库调研课题调研项目

222102210292HNKJZK-2021-61C

2024

10.3969/j.issn.1000-1379.2024.09.014

人民黄河
水利部黄河水利委员会

人民黄河

CSTPCD北大核心
影响因子：0.494
ISSN：1000-1379
年,卷(期)：2024.46(9)