AI SearchForecasting of seasonal streamflows
Call Number: AIT Thesis no. CS-94-10 Material type:
TextSeries: Asian Institute of Technology. Thesis ; no. CS-94-10Publication details: Bangkok : Asian Institute of Technology, 1994Description: 71 leavesSubject(s): Online resources: Dissertation note: Thesis (M.Eng.) - Asian Institute of Technology, 1994 Summary: In this study, the time series of monthly flows of the Mekong River and ten-day flows of the Tachia River were used to build forecasting models by using multiple regression analysis, Box Jenkins method and back propagation method. All of the forecasting methods with lead time = 1 and 2 were implemented in this study. It was found that back propagation method can obtain the best results during calibration period and Box-Jenkins models can get better results than multiple regression method in most of the cases. For forecasting seasonal flows by back propagation method, using one hidden layer network is enough to get quite satisfactory results. The forecasting accuracy for lead time= 2 (time units) is a little worse than that for lead time= 1 as expected.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
22-AIT Thesis (Replacement)
|
Asian Institute of Technology Library AIT Publications | AIT Thesis no. CS-94-10 (Browse shelf(Opens below)) | 3 | Available | 30050120676449 | |||||||||||||
40-Archives
|
Asian Institute of Technology Library Archives | AIT Thesis no. CS-94-10 (Browse shelf(Opens below)) | Available | 30050120356760 |
A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Engineering and Technology
Thesis (M.Eng.) - Asian Institute of Technology, 1994
In this study, the time series of monthly flows of the Mekong River and ten-day flows of the Tachia River were used to build forecasting models by using multiple regression analysis, Box Jenkins method and back propagation method. All of the forecasting methods with lead time = 1 and 2 were implemented in this study. It was found that back propagation method can obtain the best results during calibration period and Box-Jenkins models can get better results than multiple regression method in most of the cases. For forecasting seasonal flows by back propagation method, using one hidden layer network is enough to get quite satisfactory results. The forecasting accuracy for lead time= 2 (time units) is a little worse than that for lead time= 1 as expected.
There are no comments on this title.