Advancing Sustainable Road Construction with Multiple Regression Analysis, Regression Tree Models, and Case-Based Reasoning for Environmental Load and Cost Estimation
The construction industry, particularly in road projects, faces pressing challenges related to environmental sustainability and cost management. As road construction contributes significantly to environmental degradation and demands large-scale investments, there is an urgent need for innovative sol...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/15/12/2083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The construction industry, particularly in road projects, faces pressing challenges related to environmental sustainability and cost management. As road construction contributes significantly to environmental degradation and demands large-scale investments, there is an urgent need for innovative solutions that balance environmental impact with economic feasibility. Despite advancements in building technologies and energy-efficient materials, accurate and reliable predictions for environmental load and construction costs during the planning and design stages remain limited due to insufficient data systems and complex project variables. This study explores the application of machine-learning techniques to predict environmental loads and construction costs in road projects, using a dataset of 100 national road construction cases in the Republic of Korea. The research employs multiple regression analysis, regression tree models, and case-based reasoning (CBR) to estimate these critical parameters at both the planning and design stages. A novel aspect of this research lies in its comparative analysis of different machine-learning models to address the challenge of limited and non-ideal data environments, offering valuable insights for enhancing predictive accuracy despite data scarcity. The results reveal that while regression models perform better in the design stage, achieving error rates of 12% for environmental load estimation and 23% for construction costs, the case-based reasoning model outperforms others in the planning stage, with a 15.9% average error rate for environmental load and 19.9% for construction costs. These findings highlight the potential of machine-learning techniques to drive environmentally conscious and economically sound decision-making in construction, despite data limitations. However, the study also identifies the need for larger, more diverse datasets and better integration of qualitative data to improve model accuracy, offering a roadmap for future research in sustainable construction management. |
|---|---|
| ISSN: | 2075-5309 |