A spatial-temporal AI model with a dynamic edge-weighted GCN for both deterministic and probabilistic flood forecasting in the Shifeng River, Southeastern China

概率逻辑 计算机科学 自编码 大洪水 洪水预报 分水岭 适应性 残余物 数据挖掘 人工智能 特征(语言学) 图形 空间分析 机器学习 深度学习 空间生态学 水文模型 相关 马尔可夫链 差异(会计) 概率预测 提前期 骨料(复合) GSM演进的增强数据速率 采样(信号处理) 均方误差
作者
Ao Li,Xinlei Zhou,Yue‐Ping Xu,Yue‐Ping Xu,Yue‐Ping Xu
出处
期刊:Journal of Water and Climate Change [IWA Publishing]
卷期号:17 (10): 2767-2793
标识
DOI:10.2166/wcc.2026.069
摘要

ABSTRACT Three types of watershed spatial attributes are separately used to guide dynamic edge-weighted GCN (DynE-GCN) in learning spatial dependencies between each station's observed rainfall. Temporal dynamics are modeled by LSTM, followed by a VAE that compresses high-dimensional spatiotemporal features and reconstructs new data. Finally, by modulating the VAE output and sampling frequency, both deterministic and probabilistic flood forecasting can be performed. AI-based forecasting models have emerged as a hot topic in flood forecasting. To address the limitations of single models in uncertainty quantification and flood peak prediction, this study proposes a novel spatial-temporal AI model, GCN-VAE-ResLSTM. The model improves LSTM by utilizing a Graph Convolutional Network (GCN) with dynamic edge weights, termed DynE-GCN, to learn spatial dependencies of rainfall. Three residual connections are employed to strengthen information flow. A Variational Autoencoder (VAE) is incorporated for both extreme trend learning and uncertainty modeling. Seven series models are constructed to investigate the contributions of all modules to LSTM. Taking the Shifeng River basin in Zhejiang Province, China, as the study area, this study incorporates three watershed spatial attributes, namely hydrological network distribution, topography, and distance. Results indicate: (1) The DynE-GCN exhibits superior adaptability to spatial feature inputs. (2) The GCN-VAE-ResLSTM delivers optimal performance for deterministic predictions, reducing RMSE and PRE by 56.4 and 60.7%, respectively, compared to LSTM at a 1-hour lead time. And the GCN-VAE-LSTM delivers robust and accurate flood peak predictions at all lead times. (3) In probabilistic forecasting, the GCN-VAE-ResLSTM demonstrates the highest accuracy, while the VAE-ResLSTM achieves better sharpness, reliability, and timeliness.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
聪慧芷荷完成签到,获得积分10
刚刚
刚刚
研友_ndvmV8完成签到,获得积分10
1秒前
13867353624发布了新的文献求助10
1秒前
dog完成签到 ,获得积分10
1秒前
荒岛完成签到 ,获得积分10
1秒前
ZHANGLI完成签到 ,获得积分10
1秒前
Hello的应助被renn采纳,获得30
1秒前
1秒前
小书包完成签到,获得积分10
2秒前
凌风发布了新的文献求助10
2秒前
2秒前
SL毕业完成签到,获得积分10
2秒前
自信天真完成签到,获得积分10
2秒前
豆子发布了新的文献求助10
3秒前
3秒前
4秒前
charsiu完成签到,获得积分20
4秒前
4秒前
4秒前
小阳完成签到 ,获得积分10
4秒前
布洛芬发布了新的文献求助10
4秒前
hyc完成签到,获得积分10
5秒前
GU发布了新的文献求助10
5秒前
5秒前
okokok发布了新的文献求助10
5秒前
6秒前
跳动的蓝精灵完成签到,获得积分10
6秒前
bkagyin的应助被yangang采纳,获得10
6秒前
芥末葱发布了新的文献求助30
6秒前
青柠完成签到 ,获得积分10
6秒前
lunhui6453完成签到 ,获得积分10
7秒前
Yilo发布了新的文献求助10
7秒前
zhuo完成签到,获得积分10
8秒前
8秒前
清脆诗兰完成签到 ,获得积分10
8秒前
载酒完成签到 ,获得积分10
9秒前
张豪发布了新的文献求助10
9秒前
Fyq发布了新的文献求助30
9秒前
完美的葵阴给完美的葵阴的求助进行了留言
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184061
求助须知:如何正确求助?哪些是违规求助? 9573151
关于积分的说明 21829878
捐赠科研通 7781058
什么是DOI,文献DOI怎么找? 3434216
关于科研通互助平台的介绍 2558337
邀请新用户注册赠送积分活动 2480674