%0 Conference Paper %A Xie, Yichun %A Yang, Ji %A Zhou, Alicia %A Zhou, Chenghu %A Han, Liusheng %A Li, Yong %D 2019 %T A Computational Framework for Monitoring Black-Odorous Water from Remote Sensed Data and Data Mining Techniques. GeoComputation 2019 %U https://auckland.figshare.com/articles/conference_contribution/A_Computational_Framework_for_Monitoring_Black-Odorous_Water_from_Remote_Sensed_Data_and_Data_Mining_Techniques/9848453 %R 10.17608/k6.auckland.9848453.v2 %2 https://auckland.figshare.com/ndownloader/files/17659697 %K Black-odorous water %K Computational modeling %K Data mining %K Remote sensing %K Spectroradiometer %K Geospatial Information Systems %X China, through 40 years of the economic reforms, has witnessed fast economic growth, which has been accompanied with severe environmental challenges. One of those concerns is the surface water pollution, called black-odorous water, which has occurred in almost all big rivers as well as small streams. The Sate Council of China on April 16, 2015 unveiled its first Action Plan for Water Pollution Prevention and Control, aiming at cleaning up 70% black-odorous water in major rivers and cities by 2020. However, there are several technical challenges hindering this Action Plan: 1) What are the key indicators of black-odorous water? 2) Is the traditional direct measurement approach too time-consuming and costly for quick actions; 3) Can remote-sensing techniques be used to replace or enhance the traditional direct monitoring approach? 4) Are there effective computational algorithms for using the remote sensed data to assess the severity of black-odorous water and to identify key indicators of black-odorous water? From the perspectives of remote sensing, an effective computational framework should contain the following functions: 1) examining how each water quality indicator contributes to the severity of black-odorous water; 2) identifying which wavelength reflectances closely relate to the severity of black-odorous water; and 3) assessing which wavelength reflectances complement with what water quality indicators to reveal the most sensitive responses to the severity of black-odorous water. The paper intends to develop a computational data mining framework, which innovatively integrates the data mining techniques, such as hierarchical clustering, semisupervised discriminating, factorical analysis, spatial lasso selecting and linear regression, to answer these questions. A case study in Guangzhou City, China is carried out to demonstrate the applicability of this remote sensing based black-odorous water computational monitoring framework. %I The University of Auckland