Groundwater level prediction using Support Vektor Machines and autoregressive (AR) modelss

Abstract

Water resources managers can benefit from accurate prediction of the availability of groundwater. Ground water is a major source of water in Turkey for irrigation, water supply and industrial uses. The ground water level fluctuations depend on several factors such as rainfall, temperature, pumping etc. In this study, Hatay Amik Plain, Kumlu region was evaluated using Autoregressive (AR) and Support Vektor Machines (SVMs) methods. The monthly groundwater level was used the previous years data belonging to the Kumlu region. © 2017 Fatih Üneş, Mustafa Demirci, Yunus Ziya Kaya, Eyup Ispir, Mustafa Mamak. Published by VGTU Press. This is an open-access article distributed under the terms of the Creative Commons Attribution (CC BY-NC 4.0) License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.