摘要
使用Kolmogorov-Arnold网络(KAN)构建了一种数据驱动的水位预报方法,将水文变量的复杂关系分解为一系列一元函数的线性组合,从而准确地捕捉水文数据的变化趋势。以长江中下游莲花塘站和沙市站的流量与水位数据为基础,进行水位预报应用。结果表明,KAN模型七日平均绝对误差分别为0.187 m(莲花塘)和0.109m(沙市)。以莲花塘站为例,KAN模型相较于传统的多层感知机、长短期记忆网络、门控循环单元网络和自注意力机制模型预报精度分别提高了20.1%、45.0%、16.5%和13.0%。为了进一步提升对KAN模型的理解和认识,进行了敏感性分析和简化实验。结果表明,短期内的上游流量预报对下游水位有显著影响。KAN模型能够通过极少的模型参数揭示上游流量与下游水位变化的关系,表现出显著的可解释性。
A data-driven water level forecasting method is constructed using Kolmogorov-Arnold Networks(KAN),which decomposes the complex relationships among hydrological variables into a linear combination of univariate functions,enabling accurate capture of the trends in hydrological data.The method has been applied to water level forecasting based on discharge and water level data from the Lianhuatang and Shashi stations in the middle and lower Yangtze River.Results show the KAN model has a seven-day mean absolute error of 0.187 m at Lianhuatang and 0.109 m at Shashi.In the case of Lianhuatang,it improves forecasting accuracy by 20.1%,45.0%,16.5%,and 13.0%compared to traditional Multi-Layer Perceptron,Long Short-Term Memory network,Gated Recurrent Unit network,and Transformer models,respectively.To deepen our understanding of this model further,sensitivity analysis and simplification tests are conducted.Results indicate its short-term upstream discharge forecasting significantly affects the predicted downstream water levels.Equipped with a minimal number of parameters,it achieves effectively the relationship between upstream discharge and downstream water level changes,demonstrating remarkable interpretability.
作者
陈思宇
李肖男
花续
鲁军
荆平飞
宋志豪
CHEN Siyu;LI Xiaonan;HUA Xu;LU Jun;JING Pingfei;SONG Zhihao(State Key Laboratory of Hydroscience and Engineering,Tsinghua University,Beijing 100084,China;Changjiang Survey,Planning,Design and Research Co.,Ltd.,Wuhan 430010,China;Jiangxi Ganneng Shanggao Power Generation Co.,Ltd.,Yichun 336000,China)
出处
《水力发电学报》
2025年第4期97-107,共11页
Journal of Hydroelectric Engineering
基金
国家重点研发计划项目(2022YFC3002705)。
