Machine Learning for Slope Failure Prediction Based on Inverse Velocity and Dimensionless Inverse Velocity

Maral Malekian, Moe Momayez, Pat Bellett, Fernanda Carrea, Eranda Tennakoon

Research output: Contribution to journalArticlepeer-review

Abstract

Slope instabilities in open-pit mines pose a safety risk to workers and a financial burden on production. The direct impact of slope stability on safety and production makes slope failure predictions one of the important challenges in the mining industry. Predicting the precise time of slope failure has been the subject of much research in conjunction with the development of innovative monitoring technology designed to prevent sudden failures. This paper investigates the use of AutoRegressive Integrated Moving Average (ARIMA) model to predict the time of slope failure. Input data such as inverse velocity (IV) and dimensionless inverse velocity (DIV) from 20 slope failures were used to train the model predict the failure time. For comparison purposes, the time of slope failure using the traditional inverse velocity method is also provided. We show that ARIMA provides 90% more accurate predictions than the TIV approach.

Original languageEnglish (US)
Pages (from-to)1557-1566
Number of pages10
JournalMining, Metallurgy and Exploration
Volume40
Issue number5
DOIs
StatePublished - Oct 2023

Keywords

  • BlastVisionⓇ
  • Blasting
  • Blasts
  • GroundProbe
  • Mining
  • Slope failure
  • Slope stability

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Chemistry
  • Geotechnical Engineering and Engineering Geology
  • Mechanical Engineering
  • Metals and Alloys
  • Materials Chemistry

Fingerprint

Dive into the research topics of 'Machine Learning for Slope Failure Prediction Based on Inverse Velocity and Dimensionless Inverse Velocity'. Together they form a unique fingerprint.

Cite this