Imperial College London
Portrait Picture

ProfessorJenniferWhyte

Faculty of Engineering, Department of Civil and Environmental Engineering

Laing O'Rourke/RAEng Chair in Systems Integration
 
 
 
//

Contact

 

+44 (0)20 7594 9245j.whyte Website

 
 
//

Assistant

 

Mr Tim Gordon +44 (0)20 7594 5031

 
//

Location

 

436Skempton BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{K:2020:10.1061/(ASCE)CO.1943-7862.0001846,
author = {K, Soman R and Whyte, J},
doi = {10.1061/(ASCE)CO.1943-7862.0001846},
journal = {Journal of Construction Engineering and Management},
pages = {04020072--1--04020072--18},
title = {Codification challenges for data science in construction},
url = {http://dx.doi.org/10.1061/(ASCE)CO.1943-7862.0001846},
volume = {146},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - New forms of data science, including machine learning and data analytics, are enabled by machine-readable informationbut are not widely deployed in construction. Aqualitative study of information flow in three projects usingBuilding Information Modelling (BIM) in the late designand construction phaseis used to identify the  challenges  of  codification whichlimit the application  of  data  science.Despite substantial  efforts  to  codify information with ‘Common Data Environment(CDE)’ platforms to structure and transfer digital information within  and between  teams, participants work across  multiple  media  in both structured  and  unstructured  ways. Challenges of codification identified in this paper relate to software usage (interoperability, translation, modelling, and file-based sharing), information sharing (unstructured information, document control, workarounds, process change,and multiple CDEs), and construction process information(loss of constraints and low level of detail).  This paper contributes to the current understanding of data science in construction by articulating the codification challenges and  their implications for data  quality dimensions,such  as  accuracy,  completeness,  accessibility, consistency, timeliness, and  provenance.It concludes with  practical  implications for developingand  using machine-readable  information and  directions  for research to  extract  insight  from  data  and  support  future automation.
AU  - K,Soman R
AU  - Whyte,J
DO  - 10.1061/(ASCE)CO.1943-7862.0001846
EP  - 1
PY  - 2020///
SN  - 0733-9364
SP  - 04020072
TI  - Codification challenges for data science in construction
T2  - Journal of Construction Engineering and Management
UR  - http://dx.doi.org/10.1061/(ASCE)CO.1943-7862.0001846
UR  - https://ascelibrary.org/doi/10.1061/%28ASCE%29CO.1943-7862.0001846
UR  - http://hdl.handle.net/10044/1/76405
VL  - 146
ER  -
Download