Answers are grounded in this paper and cite their sources.
The translation of environmental awareness into operational action remains a persistent challenge in sustainable enterprise management. While digital twin technologies have advanced technical capabilities for carbon monitoring, they frequently overlook the behavioural dimensions that determine implementation outcomes. This study proposes a five-layer Explainable Behavioural Digital Twin (EBDT) framework that integrates physical enterprise sensing, behavioural encoding, and explainable artificial intelligence within a unified socio-technical architecture. Through a quantitative study of 312 enterprise decision-makers across four sectors, behavioural parameters were encoded into a multi-objective optimisation model. Results demonstrate a significant intention–implementation gap of 0.17 units (t(311) = 14.3, p < 0.001). K-means clustering identified three profiles, with Intent-Driven Deliberators (44%) as the highest-risk cohort. A real-world enterprise validation in West African manufacturing confirmed that EBDT recommendations achieved 77% implementation willingness compared with 54% for conventional optimisation, despite lower theoretical carbon reduction (18% vs. 21%). Explainability features reduced prediction error by 14.2% and offset 68% of cost sensitivity’s negative impact. These findings establish that carbon-aware systems must encode behavioural heterogeneity as a core computational primitive.
No takes yet. Share an insight, caveat, or question.
Ikeakaonwu et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: