Accurate forecasting of stream flow is of vital importance in semi-arid regions in Canada in order to meet the needs of agriculture, human needs and of wildlife. Daily stream flow discharges in semiarid and arid regions are characterized by zero-inflation, seasonality, autoregression and extreme events such as floods. Typically, flood frequency analysis estimates the level of the T-year flood based on a probability distribution model postulated for annual extrema. When many zero flow events are present, the postulated probability distribution is modified using a mixture distribution for the zero component. While an analysis based on annual maxima avoids the need for modelling seasonal variation and serial correlation, such an approach requires very long time series. Furthermore, valuable information based on daily data is not being exploited.
Hydrological issues of low flow, in particular zero flow intermittent streams that make use of daily data have received little attention in the literature. In this talk, a mixture model for logarithm of the flow-rate which accounts for zero flows, normal flowrates and extreme flows is developed, with seasonality and autoregression incorporated. Furthermore, models for the time to a flood event, the duration of a flood event, peak flow during floods and flood volume are considered in the context of zero flow intermittent streams. The statistical methods are illustrated using data from several streams in the Canadian prairie provinces.
Keywords: Zero-inflation; Flood; Seasonality; Autoregression
Biography: Dr. Melody Ghahramani is an Assistant Professor at the Department of Mathematics & Statistics, University of Winnipeg, Winnipeg, Canada.