| Abstract: | The exemplar‐aided constructor of hyper‐rectangles (EACH) model which simulates human intelligence by learning from experience and adjusting in time, proposed by Salzberb (1991), is presented and modified to strengthen its performance in variable stream flow extension. The modification is intended to resolve the contradiction between building hyper‐rectangles and predictive accuracy in which the number of hyper‐rectangles becomes too large if higher accuracy is required. To explore the feasibility of the modified EACH, a mathematical function is simulated by the model. It is then applied to extend the 10‐day stream flow records according to the nearby rainfall and/or stream flow gauges. The results show that the modified EACH achieves the goal of saving memory space and promoting predictive accuracy, and its performance is better than those of the original EACH and traditional methods. This research suggests that the modified EACH shows considerable promise in stream flow estimation. Copyright © 2000 John Wiley & Sons, Ltd. |
