|
| 基于分期自相关机器学习方法的月径流模拟与驱动机制分析 |
| Monthly Streamflow Simulation and Driving Mechanism Analysis Using Periodization-Based Autocorrelation and Machine Learning Methods |
| 投稿时间：2025-07-28 修订日期：2025-12-01 |
| DOI： |
| 中文关键词: 月径流预测 自相关性 分时期 可解释机器学习 黑河莺落峡 |
| 英文关键词: monthly runoff prediction autocorrelation staged modeling interpretable machine learning Yingluoxia Station of the Heihe River Basin |
| 基金项目:国家自然科学基金项目(52409003)；中国科协青年人才托举工程项目（YESS20240294）；北京林业大学大学生创新创业训练计划项目（202510022029） |
|
| 摘要点击次数: 45 |
| 全文下载次数: 0 |
| 中文摘要: |
| 为进一步提高月径流模拟预测精度，本文结合月径流自相关性周期性动态变化，提出一种分期自相关机器学习方法对月径流进行模拟预测。首先通过自相关函数确定自相关性分期、各分期最优滞后阶数，进而基于TOPSIS综合评分法优化模型组合，最后使用SHAP分析明确各时期影响因子驱动机制。将分期自相关机器学习方法用于中国黑河流域莺落峡水文站月径流模拟预测，结果发现：（1）莺落峡自相关性分期应为10月至翌年2月（枯水期）、3至6月（过渡期）、7至9月（丰水期），各分期最优滞后阶数分别为2个月、3个月、5个月；（2）最佳组合模型为随机森林-长短期记忆网络-随机森林组合模型（AP-RF-LSTM-RF），其纳什效率系数为0.91；较单一模型TOPSIS精度评分提高68.2%，极端径流模拟精度提高67.6%，模拟能力显著增强；（3）SHAP分析得出月径流影响关键因子为：枯水期（气温、滞后2期月径流），过渡期（降水量、滞后3期月径流）和丰水期（降水量、气温），其动态变化规律与流域水文过程相适应。结果表明该方法显著提升月尺度径流模拟精度，为月径流模拟预测提供了新工具。 |
| 英文摘要: |
| To improve monthly runoff prediction accuracy, this study proposes a staged autocorrelation machine learning method that incorporates the dynamic periodicity of runoff autocorrelation. Autocorrelation functions were first used to identify hydrological periods and optimal lag orders. Model combinations were then optimized using the TOPSIS method, and SHAP analysis was applied to interpret key driving factors. Applied to the Yingluoxia Station in the Heihe River Basin, China, the method yielded the following results: (1) The year was divided into three distinct periods：dry period (October–February)，transition period (March–June), and high-flow period (July–September)，with optimal lag orders of 2, 3, and 5 months, respectively; (2) The optimal model (AP-RF-LSTM-RF) achieved an NSE of 0.91, increasing the TOPSIS score by 68.2% and improving extreme runoff prediction by 67.6%; (3) SHAP results showed that dominant factors varied by period: temperature and 2-month-lagged runoff in the dry period, precipitation and 3-month-lagged runoff in the transition period, and both precipitation and temperature in the high-flow period. The proposed method effectively enhances model interpretability and prediction accuracy by aligning machine learning with hydrological processes. |
|
查看/发表评论 下载PDF阅读器 |
| 关闭 |