.png){kind=icon}
返回
A hybrid process-data driven framework for real-time hydrological forecasting with interpretable deep learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jhydrol.2025.134082.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• 混合XAJ-LSTM模型提高了水文预报精度。
• 贝叶斯推断增强了不确定性量化与风险评估。
• Shapley加性解释通过揭示关键变量提升了模型可解释性。
• 该框架适用于过程导向和数据驱动两类模型。
• 混合模型在精度和可靠性方面优于独立模型。
Keyword:
hybrid XAJ-LSTM model
Bayesian inference
Shapley Additive Explanations
hydrological forecasting
uncertainty quantification
期刊
IF:
6.3
论文数:
2.4W
被引数:
9.8W
机构
引用论文
分享收藏Generating Ensemble Streamflow Forecasts: A Review of Methods and Approaches Over the Past 40 Years
OAAI
OAAI分享收藏From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Multi-step-ahead time series prediction using multiple-output support vector regressionNEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Exploring a similarity search-based data-driven framework for multi-step- ahead flood forecasting
PREAI
分享收藏
Interpretable machine learning on large samples for supporting runoff estimation in ungauged basins在大样本上进行可解释的机器学习，以支持未测量流域的径流估算JOURNAL OF HYDROLOGY
JOURNAL OF HYDROLOGYIF6.3
PREAI
分享收藏Generative deep learning for probabilistic streamflow forecasting: Conditional variational auto-encoderJOURNAL OF HYDROLOGY
JOURNAL OF HYDROLOGYIF6.3
PREAI
分享收藏
查看更多内容