Mathematical Problems in Engineering
Volume 8 (2002), Issue 6, Pages 553-562

Modeling and forecasting the peak flows of a river

Mario Lefebvre

Département de mathématiques et de génie industriel, École Polytechnique de Montréal, C.P. 6079, Succursale Centre-ville, Montréal H3C 3A7, Québec, Canada

Received 10 November 2001

Copyright © 2002 Mario Lefebvre. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


A stochastic model is found for the value of the peak flows of the Mistassibi river in Québec, Canada, when the river is in spate. Next, the objective is to forecast the value of the coming peak flow about four days in advance, when the flow begins to show a marked increase. Both the stochastic model proposed in the paper and a model based on linear regression are used to produce the forecasts. The quality of the forecasts is assessed by considering the standard errors and the peak criterion. The forecasts are much more accurate than those obtained by taking the mean value of the previous peak flows.