Application of a regionalized knowledge-based model for classifying the impacts of nitrogen, sulfur, and organic acids on lakewater chemistry

T. J. Sullivan, M. C. Saunders, K. A. Tonnessen, B. L. Nash, B. J. Miller

Research output: Contribution to journalArticle

12 Scopus citations


To maintain healthy ecosystems, it is increasingly imperative that federal land managers be prepared to monitor and assess levels of atmospheric pollutants and ecological effects in national parks, wildlife refuges, and wilderness areas. Atmospheric deposition of sulfur and/or nitrogen has the potential to damage sensitive terrestrial, and especially aquatic, ecosystems and can affect the survival of in-lake and in-stream biota. Federal land managers have a need to assess, at the individual park or wilderness area level, whether surface water resources are sensitive to air pollution degradation and the extent to which they have been impacted by atmospheric deposition of sulfur or nitrogen or influenced by other complicating factors. The latter can include geologic sources of sulfur, natural organic acidity, and the influence of disturbance and land use on water quality. This paper describes a knowledge-based decision support system (DSS) network for classifying lakewater resources in five acid-sensitive regions of the United States. The DSS allows federal land managers to conduct a preliminary assessment of the status of individual lakes prior to consulting an acid-base chemistry expert. The DSS accurately portrays the decision structure and assessment outcomes of domain experts while capturing interregional differences in acidification sensitivity and historic acid deposition loadings. It is internally consistent and robust with respect to missing water chemistry input data.

Original languageEnglish (US)
Pages (from-to)55-68
Number of pages14
JournalKnowledge-Based Systems
Issue number1
Publication statusPublished - Feb 1 2005


All Science Journal Classification (ASJC) codes

  • Management Information Systems
  • Software
  • Information Systems and Management
  • Artificial Intelligence

Cite this