Journal homepage: http://www.pertanika.upm.edu.my/ SCIENCE & TECHNOLOGY e-ISSN: 2231-8526 Pertanika J. Sci. & Technol. 33 (5): 2097 - 2124 (2025) © Universiti Putra Malaysia Press Article history: Received: 28 January 2025 Accepted: 29 April 2025 Published: 11 August 2025 ARTICLE INFO E-mail addresses: rufaizal.cm@gmail.com (Rufaizal Che Mamat) azuin.ramli@puo.edu.my (Azuin Ramli) aminahbibi@puo.edu.my (Aminah Bibi Bawamohiddin) * Corresponding author DOI: https://doi.org/10.47836/pjst.33.5.04 Optimizing Carbon Footprint Estimation in Residential Construction: A Comparative Analysis of Regression Trees and ANFIS for Enhanced Sustainability Rufaizal Che Mamat 1 *, Azuin Ramli 2 and Aminah Bibi Bawamohiddin 3 1 Centre of Green Technology for Sustainable Cities, Department of Civil Engineering, Politeknik Ungku Omar, Jalan Raja Musa Mahadi, 31400 Ipoh, Perak, Malaysia 2 Centre of Research and Innovation Excellence, Politeknik Ungku Omar, Jalan Raja Musa Mahadi, 31400 Ipoh, Perak, Malaysia 3 Department of Information Technology and Telecommunications, Politeknik Ungku Omar, Jalan Raja Musa Mahadi, 31400 Ipoh, Perak, Malaysia ABSTRACT This study evaluates the predictive accuracy of Regression Trees (RTrees) and Adaptive Neuro- Fuzzy Inference Systems (ANFIS) for estimating the carbon footprint in residential construction projects. The results indicate that the ANFIS significantly outperforms the RTrees in predictive accuracy, achieving a reduction in Root Mean Square Error (RMSE) by 84.3% in the production stage (from 0.53174 to 0.08346) and by 40.4% in the operational stage (from 0.13865 to 0.08265). These improvements underscore the effectiveness of the ANFIS in capturing complex nonlinear relationships in carbon footprint data. Despite its superior accuracy, the ANFIS exhibits higher computational costs, requiring an average training time of 76.2 s, compared to 12.4 s for the RTrees. These findings highlight the trade-offs between accuracy and computational efficiency, providing valuable insights for selecting machine learning models in sustainable construction. The study concludes that integrating hybrid approaches or ensemble learning could further enhance predictive performance while maintaining efficiency. Keywords : ANFIS, carbon emission, machine learning, regression trees, sustainable construction INTRODUCTION The construction industry significantly contributes to global greenhouse gas emissions, accounting for approximately 39% of the world's final energy consumption and 37% of energy-related carbon dioxide