skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data

Abstract

We propose a new method based on the idea of delegating regressors for predicting the soil radon gas concentration (SRGC) and anomalies in radon or any other time series data. The proposed method is compared to different traditional boosting e.g., Extreme Gradient Boosting (EGB) and simple regression methods e.g., support vector regressors with linear kernel and radial kernel in terms of accurate predictions. R language has been used for the statistical analysis of radon time series (RTS) data. The results obtained show that the proposed methodology predicts SRGC more accurately when compared to different traditional boosting and regression methods. The best correlation is found between the actual and predicted radon concentration for window size of 2 i.e., two days before and after the start of seismic activities. RTS data was collected from 05 February 2017 to 16 February 2018, including 7 seismic events recorded during the study period. Findings of study show that the proposed methodology predicts the SRGC with more precision, for all the window sizes, by overlapping predicted with the actual radon time series concentrations.

Authors:
ORCiD logo [1];  [1];  [1];  [1];  [2];  [3]
  1. Univ. of Azad Jammu and Kashmir Muzaffarbad, Azad Kashmir (Pakistan)
  2. Centre for Earthquake Studies, Islamabad (Pakistan); GFZ German Research Center for Geosciences, Potsdam (Germany)
  3. Univ. of Michigan, Ann Arbor, MI (United States)
Publication Date:
Research Org.:
Univ. of Michigan, Ann Arbor, MI (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA), Office of Nonproliferation and Verification Research and Development (NA-22)
OSTI Identifier:
1616468
Grant/Contract Number:  
NA0003920; NA0002534
Resource Type:
Accepted Manuscript
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Volume: 10; Journal Issue: 1; Journal ID: ISSN 2045-2322
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; regression methods; radon anomaly; environmental data; seismic activities

Citation Formats

Rafique, Muhammad, Tareen, Aleem Dad Khan, Mir, Adil Aslim, Nadeem, Malik Sajjad Ahmed, Asim, Khawaja M., and Kearfott, Kimberlee Jane. Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data. United States: N. p., 2020. Web. doi:10.1038/s41598-020-59881-9.
Rafique, Muhammad, Tareen, Aleem Dad Khan, Mir, Adil Aslim, Nadeem, Malik Sajjad Ahmed, Asim, Khawaja M., & Kearfott, Kimberlee Jane. Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data. United States. doi:https://doi.org/10.1038/s41598-020-59881-9
Rafique, Muhammad, Tareen, Aleem Dad Khan, Mir, Adil Aslim, Nadeem, Malik Sajjad Ahmed, Asim, Khawaja M., and Kearfott, Kimberlee Jane. Thu . "Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data". United States. doi:https://doi.org/10.1038/s41598-020-59881-9. https://www.osti.gov/servlets/purl/1616468.
@article{osti_1616468,
title = {Delegated Regressor, A Robust Approach for Automated Anomaly Detection in the Soil Radon Time Series Data},
author = {Rafique, Muhammad and Tareen, Aleem Dad Khan and Mir, Adil Aslim and Nadeem, Malik Sajjad Ahmed and Asim, Khawaja M. and Kearfott, Kimberlee Jane},
abstractNote = {We propose a new method based on the idea of delegating regressors for predicting the soil radon gas concentration (SRGC) and anomalies in radon or any other time series data. The proposed method is compared to different traditional boosting e.g., Extreme Gradient Boosting (EGB) and simple regression methods e.g., support vector regressors with linear kernel and radial kernel in terms of accurate predictions. R language has been used for the statistical analysis of radon time series (RTS) data. The results obtained show that the proposed methodology predicts SRGC more accurately when compared to different traditional boosting and regression methods. The best correlation is found between the actual and predicted radon concentration for window size of 2 i.e., two days before and after the start of seismic activities. RTS data was collected from 05 February 2017 to 16 February 2018, including 7 seismic events recorded during the study period. Findings of study show that the proposed methodology predicts the SRGC with more precision, for all the window sizes, by overlapping predicted with the actual radon time series concentrations.},
doi = {10.1038/s41598-020-59881-9},
journal = {Scientific Reports},
number = 1,
volume = 10,
place = {United States},
year = {2020},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Radon emanation on San Andreas Fault
journal, February 1978


Application of an SVM-based regression model to the air quality study at local scale in the Avilés urban area (Spain)
journal, September 2011

  • Suárez Sánchez, A.; García Nieto, P. J.; Riesgo Fernández, P.
  • Mathematical and Computer Modelling, Vol. 54, Issue 5-6
  • DOI: 10.1016/j.mcm.2011.04.017

Machine learning modelling for predicting soil liquefaction susceptibility
journal, January 2011

  • Samui, P.; Sitharam, T. G.
  • Natural Hazards and Earth System Science, Vol. 11, Issue 1
  • DOI: 10.5194/nhess-11-1-2011

Radon in ground water related to seismic events
journal, August 1999


A Relationship between Linear Discriminant Analysis and the Generalized Minimum Squared Error Solution
journal, January 2005

  • Park, Cheong Hee; Park, Haesun
  • SIAM Journal on Matrix Analysis and Applications, Vol. 27, Issue 2
  • DOI: 10.1137/040607599

Anomalous radon emission as precursor of earthquake
journal, October 2009


Estimation of the radon concentration in soil related to the environmental parameters by a modified Adaline neural network
journal, February 2003


Episodic radon changes in subsurface soil gas along active faults and possible relation to earthquakes
journal, January 1980


Layered neural networks based analysis of radon concentration and environmental parameters in earthquake prediction
journal, January 2002

  • Negarestani, A.; Setayeshi, S.; Ghannadi-Maragheh, M.
  • Journal of Environmental Radioactivity, Vol. 62, Issue 3
  • DOI: 10.1016/S0265-931X(01)00165-5

Automated anomalous behaviour detection in soil radon gas prior to earthquakes using computational intelligence techniques
journal, July 2019

  • Tareen, Aleem Dad Khan; Asim, Khawaja M.; Kearfott, Kimberlee Jane
  • Journal of Environmental Radioactivity, Vol. 203
  • DOI: 10.1016/j.jenvrad.2019.03.003

An overview of statistical learning theory
journal, January 1999

  • Vapnik, V. N.
  • IEEE Transactions on Neural Networks, Vol. 10, Issue 5
  • DOI: 10.1109/72.788640

Application of decision trees to the analysis of soil radon data for earthquake prediction
journal, June 2003


Pronounced soil-radon anomaly—Precursor of recent earthquakes in India
journal, March 2007


Application of rough set and decision tree for characterization of premonitory factors of low seismic activity
journal, January 2009


Earthquake prediction model using support vector regressor and hybrid neural networks
journal, July 2018


Radon and metallic aerosols emanation before strong earthquakes and their role in atmosphere and ionosphere modification
journal, January 1997


Gradient boosting trees for auto insurance loss cost modeling and prediction
journal, February 2012


A model for the correlation between radon anomalies and magnitude of earthquakes
journal, January 1988

  • Ramola, R. C.; Singh, Surinder; Virk, H. S.
  • International Journal of Radiation Applications and Instrumentation. Part D. Nuclear Tracks and Radiation Measurements, Vol. 15, Issue 1-4
  • DOI: 10.1016/1359-0189(88)90229-4

Relation between spring water radon anomalies and seismic activity in Garhwal Himalaya
journal, August 2010


Application of artificial neural networks in simulating radon levels in soil gas
journal, February 2010


Nearest neighbor pattern classification
journal, January 1967


A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
journal, August 1997

  • Freund, Yoav; Schapire, Robert E.
  • Journal of Computer and System Sciences, Vol. 55, Issue 1
  • DOI: 10.1006/jcss.1997.1504

Seasonal variability of soil-gas radon concentration in central California
journal, October 1994


Radon in earthquake prediction research
journal, June 2011


Variations of soil radon and thoron concentrations in a fault zone and prospective earthquakes in SW Taiwan
journal, November 2005


Radon in a thermal spring: Identification of anomalies related to seismic activity
journal, June 2006


Changes in subsurface radon concentration associated with earthquakes
journal, January 1980

  • Mogro-Campero, A.; Fleischer, R. L.; Likes, R. S.
  • Journal of Geophysical Research, Vol. 85, Issue B6
  • DOI: 10.1029/JB085iB06p03053

Soil-gas radon as seismotectonic indicator in Garhwal Himalaya
journal, October 2008


Evaluating Methods for Classifying Expression Data
journal, December 2004

  • Man, Michael Z.; Dyson, Greg; Johnson, Kjell
  • Journal of Biopharmaceutical Statistics, Vol. 14, Issue 4
  • DOI: 10.1081/BIP-200035491

Earthquake Prediction Studies Using Radon as a Precursor in N-W Himalayas, India: A Case Study
journal, January 2005

  • Walia, Vivek; Virk, Hardev Singh; Yang, Tsanyao Frank
  • Terrestrial, Atmospheric and Oceanic Sciences, Vol. 16, Issue 4
  • DOI: 10.3319/TAO.2005.16.4.775(GIG)

Delegating classifiers
conference, January 2004

  • Ferri, César; Flach, Peter; Hernández-Orallo, José
  • Twenty-first international conference on Machine learning - ICML '04
  • DOI: 10.1145/1015330.1015395

machine.
journal, October 2001


Random Forests
journal, January 2001


Earthquake magnitude prediction in Hindukush region using machine learning techniques
journal, September 2016


Statistically significant relation between radon flux and weak earthquakes in the Dead Sea rift valley
journal, January 2003