Improving Data Quality with Advanced Pre-Processing of MWD Data

In geotechnical engineering, an accurate prediction is essential for the safety and effectiveness of construction projects. One example is the prediction of over/under-excavation volumes during drill and blast tunneling. Using machine learning (ML) models to predict over-excavation often results in...

Full description

Saved in:
Bibliographic Details
Main Authors: Alla Sapronova, Thomas Marcher
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Geotechnics
Subjects:
Online Access:https://www.mdpi.com/2673-7094/5/2/28
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850168540708995072
author Alla Sapronova
Thomas Marcher
author_facet Alla Sapronova
Thomas Marcher
author_sort Alla Sapronova
collection DOAJ
description In geotechnical engineering, an accurate prediction is essential for the safety and effectiveness of construction projects. One example is the prediction of over/under-excavation volumes during drill and blast tunneling. Using machine learning (ML) models to predict over-excavation often results in low accuracy, especially in complex geological settings. This study explores how the pre-processing of measurement while drilling (MWD) data impacts the accuracy of ML models. In this work, a correlational analysis of the MWD data is used as the main pre-processing procedure. For each drilling event (single borehole), correlation coefficients are calculated and then supplied as inputs to the ML model. It is shown that the ML model’s accuracy improves when the correlation coefficients are used as inputs to the ML models. It is observed that datasets made from correlation coefficients help ML models to obtain higher generalization skills and robustness. The informational content of datasets after different pre-processing routines is compared, and it is shown that the correlation coefficient dataset retains information from the original MWD data.
format Article
id doaj-art-529188a4686f47f6afe980bd0bab376f
institution OA Journals
issn 2673-7094
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Geotechnics
spelling doaj-art-529188a4686f47f6afe980bd0bab376f2025-08-20T02:20:57ZengMDPI AGGeotechnics2673-70942025-04-01522810.3390/geotechnics5020028Improving Data Quality with Advanced Pre-Processing of MWD DataAlla Sapronova0Thomas Marcher1Institute of Rock Mechanics and Tunnelling, Graz University of Technology, Rechbauerstraße 12, A8010 Graz, AustriaInstitute of Rock Mechanics and Tunnelling, Graz University of Technology, Rechbauerstraße 12, A8010 Graz, AustriaIn geotechnical engineering, an accurate prediction is essential for the safety and effectiveness of construction projects. One example is the prediction of over/under-excavation volumes during drill and blast tunneling. Using machine learning (ML) models to predict over-excavation often results in low accuracy, especially in complex geological settings. This study explores how the pre-processing of measurement while drilling (MWD) data impacts the accuracy of ML models. In this work, a correlational analysis of the MWD data is used as the main pre-processing procedure. For each drilling event (single borehole), correlation coefficients are calculated and then supplied as inputs to the ML model. It is shown that the ML model’s accuracy improves when the correlation coefficients are used as inputs to the ML models. It is observed that datasets made from correlation coefficients help ML models to obtain higher generalization skills and robustness. The informational content of datasets after different pre-processing routines is compared, and it is shown that the correlation coefficient dataset retains information from the original MWD data.https://www.mdpi.com/2673-7094/5/2/28measurement while drillingmachine learningdata analysis
spellingShingle Alla Sapronova
Thomas Marcher
Improving Data Quality with Advanced Pre-Processing of MWD Data
Geotechnics
measurement while drilling
machine learning
data analysis
title Improving Data Quality with Advanced Pre-Processing of MWD Data
title_full Improving Data Quality with Advanced Pre-Processing of MWD Data
title_fullStr Improving Data Quality with Advanced Pre-Processing of MWD Data
title_full_unstemmed Improving Data Quality with Advanced Pre-Processing of MWD Data
title_short Improving Data Quality with Advanced Pre-Processing of MWD Data
title_sort improving data quality with advanced pre processing of mwd data
topic measurement while drilling
machine learning
data analysis
url https://www.mdpi.com/2673-7094/5/2/28
work_keys_str_mv AT allasapronova improvingdataqualitywithadvancedpreprocessingofmwddata
AT thomasmarcher improvingdataqualitywithadvancedpreprocessingofmwddata