Identifying outliers of non-Gaussian groundwater state data based on ensemble estimation for long-term trends

Jina Jeong, Eungyu Park, Weon Shik Han, Kueyoung Kim, Sungwook Choung, Il Moon Chung

Research output: Contribution to journalArticlepeer-review

40 Scopus citations

Abstract

A hydrogeological dataset often includes substantial deviations that need to be inspected. In the present study, three outlier identification methods – the three sigma rule (3σ), inter quantile range (IQR), and median absolute deviation (MAD) – that take advantage of the ensemble regression method are proposed by considering non-Gaussian characteristics of groundwater data. For validation purposes, the performance of the methods is compared using simulated and actual groundwater data with a few hypothetical conditions. In the validations using simulated data, all of the proposed methods reasonably identify outliers at a 5% outlier level; whereas, only the IQR method performs well for identifying outliers at a 30% outlier level. When applying the methods to real groundwater data, the outlier identification performance of the IQR method is found to be superior to the other two methods. However, the IQR method shows limitation by identifying excessive false outliers, which may be overcome by its joint application with other methods (for example, the 3σ rule and MAD methods). The proposed methods can be also applied as potential tools for the detection of future anomalies by model training based on currently available data.

Original languageEnglish
Pages (from-to)135-144
Number of pages10
JournalJournal of Hydrology
Volume548
DOIs
StatePublished - 1 May 2017

Keywords

  • Anomaly detection
  • Interquartile range
  • Median absolute deviation
  • Outlier identification
  • Three sigma rule

Fingerprint

Dive into the research topics of 'Identifying outliers of non-Gaussian groundwater state data based on ensemble estimation for long-term trends'. Together they form a unique fingerprint.

Cite this