|
Résumé :
|
This project reports on the use of artificial neural networks (ANNs) to model the performance of a subsurface drainage system in Nova Scotia, Atlantic Canada. The ANN model was built and trained by using the observed data on midspan watertable depths and drain outflows from a subsurface-drained alfalfa field. The results were compared with the observed data, and with the simulated results from a conventional mathematical model, DRAINMOD. The results show that the ANN model can simulate midspan water-table fluctuations and drain outflows quite well. The ANN model also runs significantly faster than DRAINMOD. In addition, it requires a lot fewer inputs than DRAINMOD. The ANN simulations depend more heavily on the quality of input data ; both average as well as extreme conditions must be included. Our study indicates that an ANN model may be used effectively for design and evaluation of subsurface drainage systems. The benefits of ANNs are speed, accuracy, ease-of-use and flexibility.
|
