Groundwater Level Forecasting Using Random Forest and Linear Regression Neural Network Models

Abstract

Predicting the groundwater level has recently become very important research topic especially with the rise of population density and consequently increasing the water demand. This paper uses the Random Forest and linear regression neural network models to predict the groundwater level of Wadi-Alshaty district in the South West part of Libya. The results are compared with that obtained using the hydrologic long-term forecasting graphical approach. One of the most important findings of this study is the effectiveness of the neural network models to investigate the fluctuation of the groundwater levels over time (20 years).