Optimal Missing Value Estimation Algorithm for Groundwater Levels

Abstract

In this study an algorithm for missing data imputation is presented. The algorithm uses measurements from neighboring sensors to estimate the missing values. Data-driven approach is used and methodology chooses the optimal available combination of modeling algorithm and available measurements to produce an estimate from the model with lowest error. The methodology was tested on Ljubljana polje aquifer data and has produced close to perfect results.

Keywords

• missing values
• data cleaning
• data fusion
• sensor fusion
• machine learning
• ensembles