基于误差修正的月径流集成预测研究——以南盘江流域为例

冯德锃, 万锦, 蒋任飞, 等

doi:10.12141/j.issn.1000-565X.250255

华南理工大学学报(自然科学版) >

0 1

DOI: https://doi.org/10.12141/j.issn.1000-565X.250255

水科学与技术专题

基于误差修正的月径流集成预测研究——以南盘江流域为例

展开

1.中水珠江规划勘测设计有限公司，广东广州 510610；

2.南京信息工程大学水利部水文气象灾害机理与预警重点实验室，江苏南京 210044；

3.南京信息工程大学水文与水资源工程学院，江苏南京 210044

网络出版日期: 2025-12-09

收起

Research for Ensemble Prediction Model of Monthly Runoff Based on Error Correction

Expand

1. China Water Resources Pearl River Planning Surveying & Designing Co., Ltd., Guangzhou 510610;

2. Key Laboratory of Hydro-Meteorological Disasters Mechanism and Warning, Ministry of Water Resources, Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China;

3. College of Hydrology and Water Resources, Nanjing University of Information Science & Technology, Nanjing 210044, Jiangsu, China

Online published: 2025-12-09

Fold

摘要

中长期径流成因机制复杂，确定性预测模型误差不可避免，发掘误差成分中的径流特性可以进一步提升预测模型的预测精度。研究提出一种基于极端梯度提升（XGBoost）误差修正的长短期记忆神经网络（LSTM）月径流集成预测模型，构建上游——中游、中游——下游和上游——下游三个方向的信息流分析，采用皮尔逊相关系数筛选与月径流高相关性的气象因子作为模型输入变量，通过LSTM模型进行径流预测并获取预测误差，利用XGBoost进行误差预测，利用SHAP对研究区南盘江流域上、中、下游代表站西桥站、小龙潭站和天生桥站的误差序列进行分析，结果显示，气温、地温、气压等在一次预测中未曾利用的气象因子，其内涵特征则在二次误差预测中被发掘利用，最后将XGBoost预测误差与LSTM预测结果进行加和，获得LSTM-XGBoost集成模型的预测结果。LSTM-XGBoost集成预测模型在南盘江流域上、中、下游径流预测中，纳什效率系数可分别达到0.82、0.81和0.82，将其与随机森林模型、BP模型、单一LSTM模型、单一XGBoost模型等进行比较，发现LSTM-XGBoost集成预测模型具有更高的预测精度和可靠性。

关键词： 极端梯度提升; 误差修正; 长短期记忆神经网络; 集成预测模型; 信息流分析

本文引用格式

冯德锃, 万锦, 蒋任飞, 等 . 基于误差修正的月径流集成预测研究——以南盘江流域为例[J]. 华南理工大学学报(自然科学版), 0 : 1 . DOI: 10.12141/j.issn.1000-565X.250255

Abstract

The mechanisms behind medium and long-term runoff are complex, making errors in deterministic prediction models inevitable. Exploring the runoff characteristics within these errors can further improve the prediction accuracy of the models. This study proposes an integrated monthly runoff forecasting model based on Long Short-Term Memory (LSTM) neural networks with error correction using Extreme Gradient Boosting (XGBoost). Transfer Entropy (TE) analyses were conducted in three directional pairs: upstream to midstream, midstream to downstream, and upstream to downstream. Meteorological factors highly correlated with monthly runoff, identified via Pearson correlation, were selected as inputs to the LSTM model for initial runoff prediction. The residual errors were further modeled with XGBoost, and SHAP analysis was applied to interpret error sequences. Results show that meteorological variables such as air temperature, ground temperature, and air pressure—excluded in the first-stage LSTM prediction—were effectively exploited in the secondary error modeling. Combining XGBoost-predicted errors with LSTM outputs yielded the final predictions of the LSTM-XGBoost integrated model.Results show that the LSTM-XGBoost hybrid model achieved Nash-Sutcliffe efficiency coefficients of 0.82, 0.81, and 0.82 at the upstream, midstream, and downstream stations, respectively. Compared to models such as Random Forest, Back Propagation Neural Network (BP), standalone LSTM, and standalone XGBoost, the proposed LSTM-XGBoost model exhibited superior forecasting accuracy and reliability.

Key words： XGBoost; error correction; LSTM; ensemble prediction; transfer entropy

Options

摘要页面

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract