Prediction of Groundwater Level Based on EMD and ANN

Autor: Chun-Wei Cheng, 鄭鈞瑋
Rok vydání: 2012
Druh dokumentu: 學位論文 ; thesis
Popis: 100
Recently, the change of hydrological environment is being accelerated significantly by the impact of global warming due to climate change. It is important for the management of groundwater resources because of limited water resource. However, the use of groundwater resources efficiently relies on a more real and precise prediction model. In this study, it will seek for a reasonable and effective way to predict the changes of groundwater level by modifying the traditional method. HHT is a relatively new method to analyze time series data that possess intrinsic non-linear and non-stationary nature. By using EMD of HHT, complicated data will decompose into several IMFs that are easier to analyze. The “real-forecast” model combined from EMD, SOM and BPNN will further applied to predict the groundwater level. It shows that the predict result is more accurate than that from the traditional method. Among them, the mode of single station and multi station is adopted, but the combination mode with best performance needs to be appropriately evaluated in accordance with the characteristics of these stations.
Databáze: Networked Digital Library of Theses & Dissertations