A neural network approach to identifying non-point sources of microbial contamination

• Published in: Water research (Oxford) 1999, Vol.33 (14), p.3099-3106
• Main Authors: Brion, Gail Montgomery, Lingireddy, Srinivasa
• Format: Article
• Language: English
• Subjects: agricultural runoff; Applied sciences; Coliform bacteria; Continental surface waters; drinking water; Earth sciences; Earth, ocean, space; Engineering and environment geology. Geothermics; Exact sciences and technology; fecal coliforms; fecal flora; identification; indicators; Land use; microbial contamination; modeling; Natural water pollution; Neural networks; non-point sources; Pollution; Pollution, environment geology; Potable water; reservoirs; Reservoirs (water); Runoff; urban runoff; Water analysis; Water bacteriology; water pollution; Water quality; Water treatment and pollution; watershed management; Watersheds
• ISSN: 0043-1354; 1879-2448
• DOI: 10.1016/S0043-1354(99)00025-1

Commonly measured fecal bacteria concentrations in water and rainfall data were utilized as inputs for training a neural network model to distinguish between urban and agricultural fecal contamination present in inputs to a drinking water reservoir. Seven sites were selected that represented differing degrees of fecal contamination arising from agricultural, urban, or a blend of both land use activities. The absence of human sewage at the inlet sites to the reservoir was determined by analysis for coprostannol and serotyping of male-specific coliphage. Analyses for fecal coliform (FC), fecal streptococci (FS), total coliform (TC) and coliphage were conducted over 2 years from weekly samples collected from these sites during dry and rainy times during warm seasons. The average concentrations of microorganisms measured were highly variable and analysis of FC/FS ratios was not able to differentiate between urban or agriculturally impacted sites. A neural network model was written that used bacterial and weather data to differentiate between three site classifications: urban, agricultural and a mixture of these. The validity of the source identification, neural network model was verified through case study.