Graph neural network model for cable tunnel cost prediction under high-dimensional construction data

Ming Fang, Handong Lu and Yifeng Lai

International Journal of Innovation and Sustainable Development, 2026, vol. 20, issue 7, 76-94

Abstract: This paper focuses on the challenging problem of cable tunnel cost prediction, aiming to achieve accurate estimation with the help of advanced technology so as to improve the level of project cost management. Facing the multi-source heterogeneous data generated by cable tunnel construction - characterised by diverse engineering design parameters, construction techniques, and external environmental factors - traditional prediction methods are often ineffective. Therefore, a cost forecasting model based on graph neural network (GNN) is constructed. In this paper, various optimisation strategies are employed, including the use of weighted mean squared error (WMSE) as the loss function and the stochastic gradient descent (SGD) optimisation algorithm. The results indicate that this model is efficient and reliable for cable tunnel cost prediction and can provide strong support for engineering cost management in practical applications.

Keywords: cable tunnel; high dimensional construction data; cost forecast; GNN; graph neural network. (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.inderscience.com/link.php?id=152282 (text/html)
Open Access

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijisde:v:20:y:2026:i:7:p:76-94

Access Statistics for this article

More articles in International Journal of Innovation and Sustainable Development from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().