Simulation of groundwater level variations using wavelet combined with neural network, linear regression and support vector machine

详细信息    查看全文

• 作者：Hadi Ebrahimi ; ^{hadi_e1360@yahoo.com} ; Taher Rajaee ^{taher_rajaee@yahoo.com trajaee@qom.ac.ir}
• 关键词：Time delay neural networks ; Wavelet ; Iran ; Multi linear regression ; Groundwater level ; Support vector machine
• 刊名：Global and Planetary Change
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：148
• 期：Complete
• 页码：181-191
• 全文大小：1251 K
• 卷排序：148

文摘

Using wavelets significantly improved training of ANN and MLR models. Wavelet linear regression was the best model in groundwater level simulation. One-month-ahead of groundwater level simulated with a delay of 6 months Meyer mother wavelet was in accordance to the time series and had better results. Wavelet types had similar behavior in similar case studies.