| 李承龙,郭生练,梁志明,崔震,向鑫,张俊.基于深度学习的长江-洞庭湖流域洪水模拟预报研究[J].水利学报,2025,56(6):717-725 |
| 基于深度学习的长江-洞庭湖流域洪水模拟预报研究 |
| Flood simulation and forecasting in the Yangtze River-Dongting Lake Basin based on deep learning |
| 投稿时间：2024-09-30 |
| DOI：10.13243/j.cnki.slxb.20240630 |
| 中文关键词: 洪水预报 深度学习 卷积神经网络 长短期记忆神经网络 门控单元神经网络 长江-洞庭湖流域 |
| 英文关键词: hydrological forecasting deep learning convolutional neural network Long Short-Term Memory neural network Gated Recurrent Unit Yangtze River-Dongting Lake Basin |
| 基金项目:国家自然科学基金长江联合基金项目（U2340205）；中国长江电力股份公司科研项目（Z242402005） |
|
| 摘要点击次数: 67 |
| 全文下载次数: 42 |
| 中文摘要: |
| 精准快速地预报长江-洞庭湖流域洪水,对三峡水库防洪调度至关重要。本文构建了卷积神经网络（CNN）、长短期记忆神经网络（LSTM）和门控循环单元（GRU）三个深度学习模型,采用2010—2023年汛期（5—9月）8个水文站和301个雨量站观测资料进行参数率定和模型验证。研究结果表明：这三个模型的洪水模拟预报精度都很高,其中GRU模型性能最优,训练期和验证期24 h预报结果的纳什效率系数（NSE）分别达到0.993和0.988,总径流相对误差分别为0.25%和-0.26%；对于验证期洪峰超过20 000 m3/s的6场洪水,三个模型的预报结果差异较大,GRU模型明显优于LSTM和CNN,其NSE大于0.85,洪峰绝对误差控制在2%以内。GRU和LSTM深度学习模型具有较高的模拟精度和较强的泛化能力,可为复杂的长江-洞庭湖流域洪水预报提供一种新的途径。 |
| 英文摘要: |
| Accurate and fast flood forecasting in the Yangtze River-Dongting Lake basin is vitally important for flood control operation of the Three Gorges Reservoir. Three deep learning models, namely the Convolutional Neural Network （CNN）, the Long Short-Term Memory neural network （LSTM）, and the Gated Recurrent Unit （GRU）, were constructed. The recorded flow discharges and rainfalls of eight hydrological stations and 301 rain gauge stations during flood season （from May to September） from 2010 to 2023 were used to calibrate and verify these models. The results show that the flood simulation and forecasting accuracy of these deep learning models are all sufficiently high. Among them, the GRU model performs the best, with the Nash-Sutcliffe Efficiency （NSE） in the 24-hour forecast horizon reaching 0.993 during the training period and 0.988 during the testing period, and the total runoff relative errors being 0.25% and -0.26%, respectively. For the 6 flood events with peak flows exceeding 20,000 m3/s during the testing period, the forecast results of the three models vary significantly. The GRU model is superior to LSTM and CNN models, with the NSE values greater than 0.85, and the absolute errors of peak flow less than 2%. The GRU and LSTM models have high simulation accuracy and strong generalization ability, which can provide a new approach for complex flood forecasting in the Yangtze River-Dongting Lake Basin. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|