AWWA IMTECH57907

The use of automated data technologies in data-reliant industries is currently on the rise due to increasing size and complexity of databases. In the drinking water treatment industries, utilities routinely collect a variety of data to assist in process operation, administrative decision making, and regulatory compliance. This data typically resides in multiple locations within a utility's data network, contains frequent erroneous values, and contains valuable information awaiting discovery. This paper discusses three related data technologies, i.e., data manipulation, data cleansing, and data mining, and their usefulness to data management in the industry. Three case studies are presented that demonstrate how data are manipulated, cleansed of errors, and mined for new and useful information. Includes 15 references, tables, figures.