A knowledge-based expert system for flood frequency analysis

Abstract

Single-station flood frequency analysis is an important element in hydrotechnical planning and design. In Canada, no single statistical distribution has been specified for floods; hence, the conventional approach is to select a distribution based on its fit to the observed sample. This selection is not straightforward owing to typically short record lengths and attendant sampling error, magnified influence of apparent outliers, and limited evidence of two populations. Nevertheless, experienced analysts confidently select a distribution for a station based only on a few heuristics. A knowledge-based expert system has been developed to emulate these expert heuristics. It can perform data analyses, suggest an appropriate distribution, detect outliers, and provide means to justify a design flood on physical grounds. If the sample is too small to give reliable quantile estimates, the system performs a Bayesian analysis to combine regional information with station-specific data. The system was calibrated and tested for 52 stations across Canada. Its performance was evaluated by comparing the distributions selected by experts with those given by the developed system. The results indicated that the system can perform at an expert level in the task of selecting distributions. Key words: flood frequency, expert system, single-station, fuzzy logic, inductive reasoning, production system.

Homogeneous region delineation based on annual flood generation mechanisms

“…The many drawbacks of parametric frequency analysis make distribution selection a difficult task, as exemplified by the complexity of an expert system for flood frequency analysis (Chow & Watt, 1990).…”

REGIONAL FLOOD EQUATIONS FOR THE PROVINCES OF ONTARIO AND QUEBEC1

“…Parametric fitting of distributions presents numerous difficulties related to the unimodal shape of the theoretical distributions and the extrapolation of the right-hand tail, among others. Fitting a distribution is considered a subjective exercise at times, and often a very difficult one, as exemplified by the complexity of an expert system for flood frequency analysis (Chow and Watt, 1990). An alternative approach involving nonparametric methods, which does not require a possibly erroneous assumption with regard to distribution selection, has been successfully investigated by many researchers (Adamowski, 1985(Adamowski, , 1989Bardsley, 1989;Guo, 1991).…”

Application of knowledge management to environmental management projects: A case study for lake management

“…1989), classification of species (Domingo 1996), control of enterprise budgets in aquaculture (Bolte et al . 2000), water quality management (Scheer & Masera 1993) and disaster prevention (Chow & Watt 1990). All these systems have limited objectives, however, and are not appropriate for storing and disseminating various kinds of data or information.…”