当前位置: X-MOL 学术J. Hydrol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Neurocomputing in Surface Water Hydrology and Hydraulics: A Review of Two Decades Retrospective, Current Status and Future Prospects
Journal of Hydrology ( IF 5.9 ) Pub Date : 2020-09-01 , DOI: 10.1016/j.jhydrol.2020.125085
Mohammad Zounemat-Kermani , Elena Matta , Andrea Cominola , Xilin Xia , Qing Zhang , Qiuhua Liang , Reinhard Hinkelmann

Abstract Neurocomputing methods have contributed significantly to the advancement of modelling techniques in surface water hydrology and hydraulics in the last couple of decades, primarily due to their vast performance advantages and usage amenity. This comprehensive review considers the research progress in the past two decades, the current state-of-the-art, and future prospects of the application of neurocomputing to different aspects of hydrological sciences, i.e., quantitative surface hydrology and hydraulics. An extensive literature survey, by running over more than 800 peer-reviewed papers, outlines and concisely explores the past and recent tendencies in the application of conventional neural-based approaches and modern neurocomputing models in relevant topics of hydrological and hydraulic sciences. Apart from segregated descriptions and analyses of the main facets of surface hydrology and hydraulics, this review offers a practical summary of prevailing neurocomputing methods used in different subfields of hydrology and water engineering. Six relevant topics to modelling hydrological and hydraulic sciences are articulated and analysed, including modelling of water level in surface water bodies, flood and risk assessment, sediment transport in river systems, urban water demand prediction, modelling flow through hydro-structures, and hydraulics of sewers. This review is meant to be a mainstream guideline for researchers and practitioners whose work is associated with data mining and machine learning methods in various areas of water engineering and hydrological sciences to assist them to decide on suitable methods, network structures and modelling strategies for a given problem.

中文翻译:

地表水水文学和水力学中的神经计算:两个十年的回顾、现状和未来展望

摘要 在过去的几十年里,神经计算方法对地表水水文学和水力学建模技术的进步做出了重大贡献,这主要是由于其巨大的性能优势和使用便利性。这篇综合综述考虑了过去 20 年的研究进展、当前最先进的技术以及神经计算在水文科学不同方面(即定量地表水文学和水力学)的应用的未来前景。一项广泛的文献调查,通过运行 800 多篇同行评审论文,概述并简明地探讨了传统基于神经的方法和现代神经计算模型在水文和水利科学相关主题中应用的过去和最近的趋势。除了对地表水文学和水力学的主要方面进行分离描述和分析外,本综述还对水文学和水工程不同子领域中使用的流行神经计算方法进行了实用总结。阐述和分析了与水文和水利科学建模的六个相关主题,包括地表水体水位建模、洪水和风险评估、河流系统中的泥沙输送、城市需水量预测、通过水文结构的流量建模和水力学。下水道。这篇综述旨在成为研究人员和从业人员的主流指南,他们的工作与水工程和水文科学各个领域的数据挖掘和机器学习方法相关,以帮助他们决定合适的方法,
更新日期:2020-09-01
down
wechat
bug