.png){kind=icon}
.png){kind=icon}
Return
Contract-Integrated Environmental Impact Intelligence System
.png){kind=icon}
OA
AI
DOI：10.3390/su18136789.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study addresses the disconnect between environmental impact assessment (EIA) outputs and construction contract management, which limits the practical effectiveness of environmental decision-making in project delivery. To bridge this gap, ImpactPredict—a data-driven decision-support framework—is developed to integrate environmental impact data with environmental-based contractual risk assessment. The methodology combines: (1) severity–likelihood environmental scoring with contractual weighting to generate quantitative indicators of claim likelihood before and after mitigation; (2) developing the proposed framework using Microsoft Excel and Power BI; (3) validation using six case study energy projects in Egypt, enabling cross-case comparative analysis; and (4) statistical analysis to test the model’s sensitivity and uncertainty. The results show consistent reductions across all projects, with mitigation leading to an average 40% risk reduction across all case studies, and significant decreases in predicted claims. Linear regression analysis between initial contractual risk (CR) and residual contractual risk (RCR) produced the predictive equation R C ^ R = 4.93 + 0.351(CR). The regression coefficient and hypothesis testing (t = 3.367, p = 0.028 < 0.05) provide preliminary evidence that initial contractual risk is a statistically significant predictor of residual contractual risk. The coefficient of determination (R2 = 0.758) indicates that approximately 75.8% of the variance in residual risk is explained by the initial risk conditions. In addition, low prediction error values (mean absolute error = 1.17; root mean square error = 1.28) demonstrate satisfactory predictive stability and model reliability. The sensitivity analysis indicates that the model exhibits proportional responsiveness to all input variables, with severity and likelihood identified as dominant drivers of risk magnitude, while contractual weighting governs risk translation into project performance outcomes. These findings confirm that environmental impacts can be operationalized as quantifiable contractual risk drivers. The study concludes that embedding contract-integrated environmental intelligence within accessible analytical platforms enhances decision-making, supports measurable performance improvement, and transforms EIA into a proactive risk management tool.
Keywords:
construction management
contracts
decision-making
environmental impact assessment
environmental management
risk assessment
Journal
IF:
3.3
Papers:
10.6W
Citations:
28.4W