Application of AI Techniques for Identification of Unknown Groundwater Pollution Sources
Other Publication ResearchOnline@JCUAbstract
A new methodology for the identification of unknown groundwater pollution sources under uncertainties and sparsity of data is developed. This methodology is based on the concept of Artificial Intelligence, machine learning and optimal statistical pattern recognition using Bayes' Optimal Decision Rule. The function of the optimal pattern recognition system is to optimally match extracted features of the simulated breakthrough curves with observed sets of concentration measurements in the field with a comparable set obtained by simulating groundwater transport for various candidate disposal conditions. In order to make the application of this methodology more practical, an Expert System (ES) was developed. The Expert System uses the results obtained by applying the optimal pattern-recognition algorithm to select a particular set of pollution-source locations and magnitudes. The Expert System also has the capability of adding measures of confidence to alternative selections of sources made by the pattern-recognition system, such that these solutions can be ranked according to the subjective confidences supplied by the users. The performance of the pattern-recognition system and the Expert System was evaluated for a selected study area.
Journal
N/A
Publication Name
Water Pollution: Modelling, Measuring and Prediction
Volume
N/A
ISBN/ISSN
978-94-011-3694-5
Edition
N/A
Issue
N/A
Pages Count
17
Location
N/A
Publisher
Springer
Publisher Url
N/A
Publisher Location
Dordrecht, NLD
Publish Date
N/A
Url
N/A
Date
N/A
EISSN
N/A
DOI
10.1007/978-94-011-3694-5_5