基于深度信念极限学习机与卷积优化算法的洪水预报方法
Flood Prediction Method Based on Deep Belief Extreme Learning Machine and Convolution Optimization Algorithm
徐军杨 1张奇伟 1蔡鹏 1罗远林 1张坚 2张楚3
作者信息
- 1. 华东勘测设计研究院有限公司,浙江 杭州 311122
- 2. 昆山市水务局,江苏 苏州 215131
- 3. 淮阴工学院自动化学院,江苏 淮安 223003
- 折叠
摘要
针对洪水峰高量大、汇流时间短以及流域地貌复杂,导致洪水预报难度大和预报精度不理想的问题,提出一种基于深度信念极限学习机(DBN-ELM)和改进卷积优化算法(ICOA)的ICOA-DBN-ELM模型.以渭河上游北道水文站点2006～2020年的日径流数据作为输入数据,并将该模型与 BP、ELM、DBN-BP、DBN-ELM、COA-DBN-ELM模型进行对比.结果表明,所建立的ICOA-DBN-ELM模型有更好的预报精度,在洪水预报领域具有良好的应用前景.
Abstract
The ICOA-DBN-ELM model based on deep belief network(DBN),extreme learning machine(ELM)and improved convolution optimization algorithm(ICOA)is proposed to solve the problems of flood prediction difficulty and unsatisfactory accuracy caused by large flood peak,short convolution time and complex basin topography.The daily run-off data of the Beidao hydrological station in the upper reaches of the Wei River from 2006 to 2020 were used as input da-ta,and the model was compared with BP,ELM,DBN-BP,DBN-ELM and COA-DBN-ELM models.The results show that the established ICOA-DBN-ELM model has better prediction accuracy,and has a good application prospect in the field of flood prediction.
关键词
洪水预报/深度信念极限学习机/参数优化/卷积优化算法Key words
flood forecasting/deep belief extreme learning machine/parameter optimization/convolution optimiza-tion algorithm引用本文复制引用
基金项目
国家自然科学基金项目(62303191)
江苏省自然科学基金项目(BK20191052)
江苏省高校自然科学基金面上项目(23KJD480001)
江苏省双创计划(JSSCBS20201037)
出版年
2024
NETL
NSTL
万方数据