You are here:
Integrated Data Fusion and Mining Techniques for Monitoring Total Organic Carbon Concentrations in a Lake
Chang, N., B. W. Vannah, J. Yang, AND M. Elovitz. Integrated Data Fusion and Mining Techniques for Monitoring Total Organic Carbon Concentrations in a Lake. INTERNATIONAL JOURNAL OF REMOTE SENSING. Taylor & Francis, Inc., Philadelphia, PA, 35(3):1064-1093, (2014).
To inform the scientific community of drinking water treatement research.
Total organic carbon (TOC) in surface waters, markedly of seasonal variations, is a known precursor of disinfection byproducts such as Total Trihalomethanes (TTHM) in drinking water treatment. Real-time knowledge of TOC distribution in source water can help treatment operation to minimize the byproduct generation. In this paper, we have proposed an early warning system using Integrated Data Fusion and Machine-learning (IDFM) Techniques to estimate TOC level and distribution by measuring the water body’s surface reflectance. Landsat satellite imageries have high spatial resolution, but their application suffers from long overpass interval of 16 days. Free coarse resolution sensors with frequent revisit times, such as Moderate Resolution Imaging Spectroradiometer (MODIS), are incapable of providing detailed water quality information because of low spatial resolution. This methodology difficulty is resolved by using the data fusion techniques, in which the high spatial resolution Landsat and the high temporal resolution MODIS imageries are combined to produce synthetic images in both high spatial and temporal resolutions. As a demonstration, the case study described here utilizes the band data from the fused products and applied machine-learning techniques to reconstruct the spatiotemporal TOC distribution in Harsha Lake, a small reservoir in Ohio for drinking water production in a nearby plant. Analysis of the results using 4 statistical indices confirmed that the genetic programming (GP) model accurately estimated the temporal variations of TOC concentration in the lake.
Record Details:Record Type: DOCUMENT (JOURNAL/PEER REVIEWED JOURNAL)
Organization:U.S. ENVIRONMENTAL PROTECTION AGENCY
OFFICE OF RESEARCH AND DEVELOPMENT
NATIONAL RISK MANAGEMENT RESEARCH LABORATORY
WATER SUPPLY AND WATER RESOURCES DIVISION
URBAN WATERSHED MANAGEMENT BRANCH