Predicting Multiple Functions of Sustainable Flood Retention Basins under Uncertainty via Multi-Instance Multi-Label Learning

作     者：Yang, Qinli Boehm, Christian Scholz, Miklas Plant, Claudia Shao, Junming 

作者机构：Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Big Data Res Ctr Chengdu 611731 Peoples R China Univ Munich Inst Comp Sci D-80937 Munich Germany Univ Salford Sch Comp Sci & Engn Civil Engn Res Grp Salford M5 4WT Lancs England Helmholtz Zentrum Munich German Res Ctr Environm Hlth D-85764 Neuherberg Germany 

出 版 物：《WATER》 (水)

年 卷 期：2015年第7卷第4期

页      面：1359-1377页

核心收录：

学科分类：0830[工学-环境科学与工程（可授工学、理学、农学学位）] 08[工学] 081501[工学-水文学及水资源] 0815[工学-水利工程] 

基　　金：European Regional Development Fund Interreg IVB North Sea Region Program University of Edinburgh University of Salford Natural Science Foundation of China Fundamental Research Funds for the Central Universities [ZYGX2014J091] Postdoctoral Science Foundation of China [2014M552344] 

主　　题：sustainable flood retention basin function assessment uncertainty multi-instance multi-label learning classification 

摘      要：The ambiguity of diverse functions of sustainable flood retention basins (SFRBs) may lead to conflict and risk in water resources planning and management. How can someone provide an intuitive yet efficient strategy to uncover and distinguish the multiple potential functions of SFRBs under uncertainty? In this study, by exploiting both input and output uncertainties of SFRBs, the authors developed a new data-driven framework to automatically predict the multiple functions of SFRBs by using multi-instance multi-label (MIML) learning. A total of 372 sustainable flood retention basins, characterized by 40 variables associated with confidence levels, were surveyed in Scotland, UK. A Gaussian model with Monte Carlo sampling was used to capture the variability of variables (i.e., input uncertainty), and the MIML-support vector machine (SVM) algorithm was subsequently applied to predict the potential functions of SFRBs that have not yet been assessed, allowing for one basin belonging to different types (i.e., output uncertainty). Experiments demonstrated that the proposed approach enables effective automatic prediction of the potential functions of SFRBs (e.g., accuracy 93%). The findings suggest that the functional uncertainty of SFRBs under investigation can be better assessed in a more comprehensive and cost-effective way, and the proposed data-driven approach provides a promising method of doing so for water resources management.