Human-machine collaboration enabled infrastructure sustainability: A scenario-based selection framework

Abstract

Human-machine collaboration (HMC) is a pivotal enabler for infrastructure sustainability (IS), yet existing studies neglect hierarchical dependencies among HMC scenarios and lack quantitative tools to examine the probabilistic associations between HMC scenarios and IS. To address these gaps, this study develops a systematic HMC scenario selection framework. First, 13 critical HMC scenarios spanning the infrastructure design, construction, and operation and maintenance (O&M) phases were identified through a systematic literature review and semi-structured expert interviews. Subsequently, a hybrid Interpretive Structural Modeling-Bayesian Network (ISM-BN) approach was employed. ISM mapped an eight-tier hierarchical structure, while BN estimated model-inferred probability changes associated with HMC scenarios across economic (ECSU), environmental (ENSU), and social (SOSU) sustainability dimensions using 147 valid survey responses from sustainable infrastructure demonstration projects in mainland China. Finally, a two-dimensional “priority-contribution” decision framework was constructed, integrating ISM-derived implementation priority and BN-inferred perceived sustainability contribution. Results indicate that, within the surveyed demonstration-project context, Smart Energy Management (SEM) shows the highest perceived overall IS contribution within the current survey-based BN model, followed by Generative Design and Multi-scheme Optimization (GDMSO) and Automated Quantity Surveying and Cost Estimation (AQSCE). This study characterizes probabilistic association patterns between HMC scenarios and IS outcomes and offers an evidence-informed tool for HMC investment decisions in mainland China’s sustainable infrastructure context.

Keywords

Infrastructure sustainability / Human-machine collaboration scenarios / Decision framework

Rights & permissions

Higher Education Press 2026

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.