Long-Term Groundwater Level Prediction Model Based on Hybrid KNN-RF Technique

Omar Kombo,Yahya Sheikh,Santhi Kumaran,Kayalvizhi Jayavel,Alastair Bovim

doi:10.3390/hydrology7030059

Abstract

Reliable seasonal prediction of groundwater levels is not always possible when the quality and the amount of available on-site groundwater data are limited. In the present work, a hybrid K-Nearest Neighbor-Random Forest (KNN-RF) is used for the prediction of variations in groundwater levels (L) of an aquifer with the groundwater relatively close to the surface (<10 m) is proposed. First, the time-series smoothing methods are applied to improve the quality of groundwater data. Then, the ensemble K-Nearest Neighbor-Random Forest (KNN-RF) model is treated using hydro-climatic data for the prediction of variations in the levels of the groundwater tables up to three months ahead. Climatic and groundwater data collected from eastern Rwanda were used for validation of the model on a rolling window basis. Potential predictors were: the observed daily mean temperature (T), precipitation (P), and daily maximum solar radiation (S). Previous day’s precipitation P (t − 1), solar radiation S (t), temperature T (t), and groundwater level L (t) showed the highest variation in the fluctuations of the groundwater tables. The KNN-RF model presents its results in an intelligible manner. Experimental results have confirmed the high performance of the proposed model in terms of root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe (NSE), and coefficient of determination (R2).

Highlights

Groundwater is the most critical source of fresh water that serves about one-third of the world’s water demands
The predictive capacity of the K-Nearest Neighbor-Random Forest (KNN-Random forest (RF)) technique was investigated and the results were predictions at the Mukarange borehole using the K-nearest neighbor (KNN)-RF, RF, support vector machine (SVM), artificial neural network (ANN), and KNN models are compared to the four general models
The KNN model obtained the best results for the short term (15–30 day-ahead), while RF

Summary

Introduction

Groundwater is the most critical source of fresh water that serves about one-third of the world’s water demands. Socio-economic development is closely linked with the availability and accessibility of groundwater resources [1]. 36% of the domestic freshwater supply, 42% of water for agriculture, and 27% of the industrial water demand come from groundwater [2,3,4,5]. While the world’s water demand is expected to rise significantly in the future [6], recent studies report an intensive drop in groundwater levels in many parts of the world [7,8,9,10]. Diminished precipitation and high temperature can lead to reduced groundwater levels during dry periods [15]. The increased dependence on groundwater, Hydrology 2020, 7, 59; doi:10.3390/hydrology7030059 www.mdpi.com/journal/hydrology

Methods

Results

Conclusion