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.