缺资料地区可解释性混合机器学习模型中长期径流预报

doi:10.11988/ckyyb.20240319

raybet体育在线院报 ›› 2025, Vol. 42 ›› Issue (7): 52-59.DOI: 10.11988/ckyyb.20240319

缺资料地区可解释性混合机器学习模型中长期径流预报

由宇军¹(), 白云岗², 卢震林²(), 张江辉², 曹彪², 李文忠³, 余其鹰³

¹ 陕西省水文水资源勘测中心,西安 710068
² 新疆水利水电科学研究院,乌鲁木齐 830049
³ 郑州大学水利与交通学院,郑州 450001

收稿日期:2024-04-02 修回日期:2024-07-08 出版日期:2025-07-01 发布日期:2025-07-01
通信作者:
卢震林(1980-),男,甘肃民勤人,正高级工程师,硕士,研究方向为水文与水资源。E-mail:59963111@qq.com
作者简介:
由宇军(1974-),男,陕西蒲城人,高级工程师,主要从事水文勘测、水文情报预报等工作。E-mail:506819440@qq.com
基金资助:
新疆维吾尔自治区重点研发计划项目(2023B02044-3); 新疆“天山英才-科技创新领军人才”项目(2022TSYCLJ0069)

Medium- Long-Term Runoff Forecasting Using Interpretable Hybrid Machine Learning Model for Data-Scarce Regions

YOU Yu-jun¹(), BAI Yun-gang², LU Zhen-lin²(), ZHANG Jiang-hui², CAO Biao², LI Wen-zhong³, YU Qi-ying³

¹ Shaanxi Hydrology and Water Resources Survey Center, Xi’an 710068, China
² Xinjiang Research Institute of Water Resources and Hydropower,Urumqi 830049,China
³ School of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou 450001, China

Received:2024-04-02 Revised:2024-07-08 Published:2025-07-01 Online:2025-07-01

摘要/Abstract

摘要：

在无资料地区气象、水文等观测资料缺乏,影响径流预报的准确性,直接影响水文预报和防汛抗旱工作的开展。分析无资料地区现有的降水、气温和径流数据在中长期预报中的适用性,进而实现径流预报非常重要。分别采用卷积神经网络算法(CNN)、双向门控循环神经网络(BiGRU)、注意力机制(Attention)和优化粒子群算法(IPSO)构建CNN-BiGRU-Attention、IPSO-CNN-BiGRU-Attention组合模型,再与门控循环单元模型(GRU)和ABCD水量平衡模型进行对比分析,并在玉龙喀什河进行综合评估,并结合SHAP可解释性机器学习方法探究最优模型中输入特征对径流影响的贡献程度。结果表明:加入降水和气温的组合模型IPSO-CNN-BiGRU-Attention预测精度整体优于CNN-BiGRU-Attention、GRU模型,与实际值能够较好地吻合;随着预见期的增加,提出的组合模型在验证期内均方根误差(RMSE)、平均绝对误差(MAE)、平均绝对百分误差(MAPE)、纳什效率系数(NSE)分别为2.11、1.32 m³/s、73.76%和0.94,并且在前3个月预报精度最高。该方法在缺资料地区月径流预报中具有较好的效果。

关键词: 径流预报, 缺资料地区, SHAP可解释性机器学习方法, 组合模型IPSO-CNN-BiGRU-Attention, 预测精度

Abstract:

[Objectives] This study aims to analyze the applicability of existing precipitation, temperature, and runoff data in data-scarce regions, and to develop and evaluate a deep learning hybrid model driven by multi-source information for improving the accuracy of monthly runoff forecasting. [Methods] Based on historical precipitation, temperature, and runoff sequences from the Yulongkashi River, a Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Attention (CNN-BiGRU-Attention) model was developed. An Improved Particle Swarm Optimization (IPSO) algorithm was used to optimize this model, forming the IPSO-CNN-BiGRU-Attention hybrid model. The performance of this model was compared with that of the Gated Recurrent Unit (GRU) model and the ABCD water balance model. [Results] The IPSO-CNN-BiGRU-Attention model that incorporated precipitation and temperature data overall outperformed the CNN-BiGRU-Attention and GRU models, showing better agreement with the observed values. As the predication period increased, the proposed model achieved a root mean square error (RMSE) of 2.11 m³/s, a mean absolute error (MAE) of 1.32 m³/s, a mean absolute percentage error (MAPE) of 73.76%, and a Nash-Sutcliffe efficiency (NSE) coefficient of 0.94. The highest forecast accuracy was observed in the first three months. [Conclusions] The IPSO-CNN-BiGRU-Attention model effectively integrates precipitation, temperature, and runoff information, significantly enhancing the accuracy of monthly runoff forecasts in data-scarce regions. The model demonstrates robust performance across different forecast horizons, particularly suitable for short-term predictions of 1-3 months. This approach offers a practical and reliable tool for hydrological forecasting and flood control/drought management in data-scarce basins.

Key words: runoff forecasting, data-scarce regions, SHAP interpretable machine learning analysis, IPSO-CNN-BiGRU-Attention model, prediction accuracy

中图分类号:

TV121径流

由宇军, 白云岗, 卢震林, 张江辉, 曹彪, 李文忠, 余其鹰. 缺资料地区可解释性混合机器学习模型中长期径流预报[J]. raybet体育在线院报, 2025, 42(7): 52-59.

YOU Yu-jun, BAI Yun-gang, LU Zhen-lin, ZHANG Jiang-hui, CAO Biao, LI Wen-zhong, YU Qi-ying. Medium- Long-Term Runoff Forecasting Using Interpretable Hybrid Machine Learning Model for Data-Scarce Regions[J]. Journal of Changjiang River Scientific Research Institute, 2025, 42(7): 52-59.

图/表 9

图1 卷积神经网络特征提取示意图

Fig.1 Schematic diagram of feature extraction using convolutional neural network

图2 BiGRU模型结构示意图

Fig.2 Schematic diagram of BiGRU model structure

图3 改进的粒子群优化算法(IPSO)超参数寻优执行流程

Fig.3 Execution flowchart of hyperparameter optimization usingImproved Particle Swarm Optimization (IPSO) algorithm

图4 ICBA径流模型预报过程图

Fig.4 Forecasting process of ICBA runoff model

图5 同站气温、降水、径流年内变化

Fig.5 Annual variations of temperature, precipitation, and runoff at the same station

图6 3种机器模型和ABCD水文模型验证期径流预报对比

Fig.6 Comparison of runoff forecasts during model validation period between the three machine learning models and ABCD model

表1 组合模型预报评价指标统计

Table 1 Statistical summary of evaluation metrics for hybrid model forecast

预见期/月	模型	率定期				验证期
预见期/月	模型	MAPE/ %	RMSE/ %	MAE/ %	NSE/ %	MAPE/ %	RMSE/ %	MAE/ %	NSE/ %
1	ICBA	35	28	37	12	32	26	32	10
1	CBA	26	20	26	9	27	21	22	9
2	ICBA	33	24	34	8	35	24	30	9
2	CBA	18	15	18	7	16	14	18	7
3	ICBA	35	22	35	8	28	22	28	7
3	CBA	16	14	17	7	14	12	19	7
4	ICBA	23	17	28	6	22	17	24	6
4	CBA	16	12	16	5	15	11	16	5
5	ICBA	18	14	20	6	18	14	18	6
5	CBA	15	12	15	4	13	10	12	5
6	ICBA	16	15	16	5	14	15	14	5
6	CBA	9	11	8	4	7	9	6	4

图7 GRU、ICBA、CBA模型鲁棒性评估结果

Fig.7 Robustness assessment results of GRU, ICBA, and CBA models

图8 历史月径流、气温、降水对模型预测贡献度的分布

Fig.8 Contribution distribution of historical monthly runoff,temperature,and precipitation to model prediction

[1]	杨晨蕾, 包腾飞. 基于FCM-XGBoost的大坝变形预测模型[J]. raybet体育在线院报, 2021, 38(8): 66-71.
[2]	贺波, 马静, 高赫余. 基于多粒度特征和XGBoost模型的城市日供水量预测[J]. raybet体育在线院报, 2020, 37(5): 43-49.
[3]	胡安玉, 包腾飞, 杨晨蕾, 张静缨. 基于LSTM-Arima的大坝变形组合预测模型及其应用[J]. raybet体育在线院报, 2020, 37(10): 64-68.
[4]	董丹丹, 祖安君, 孙雪莲. 基于GACO-BP-MC的大坝变形监控模型[J]. raybet体育在线院报, 2019, 36(7): 48-54.
[5]	包丽娜, 唐德善, 胡晓波, 楚士冀. 基于小波分解及Arima误差修正的径流预测模型及应用[J]. raybet体育在线院报, 2018, 35(12): 18-21.
[6]	周建中, 彭甜. 长江上游径流混沌动力特性及其集成预测研究[J]. raybet体育在线院报, 2018, 35(10): 1-9.
[7]	邱子锋, 沈简, 傅旭东, 罗浩威. 基于最优加权组合预测的隧道监控量测数据分析[J]. raybet体育在线院报, 2016, 33(5): 53-57.
[8]	杨皓翔, 梁川, 崔宁博. 基于加权灰色-马尔可夫链模型的城市需水预测[J]. raybet体育在线院报, 2015, 32(7): 15-21.
[9]	王文梅, 孙蓉琳, 高岩. 岩溶地区径流预报中BP网络的改进[J]. raybet体育在线院报, 2012, 29(4): 11-16.

缺资料地区可解释性混合机器学习模型中长期径流预报

Medium- Long-Term Runoff Forecasting Using Interpretable Hybrid Machine Learning Model for Data-Scarce Regions

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

相关文章 9

编辑推荐

Metrics

本文评价