In the heart of India’s burgeoning construction sector, a pressing challenge looms large: construction and demolition (C&D) waste. As urbanization accelerates, so does the mountain of waste, posing significant environmental and economic hurdles. Enter Choudhury Gyanaranjan Samal, a researcher from the School of Civil Engineering at KIIT Deemed to be University in Bhubaneswar, who has embarked on a mission to tackle this issue head-on. His recent study, published in the journal *Construction Materials* (translated to English as “Building Materials”), offers a fresh, data-driven perspective on C&D waste, combining industry insights with cutting-edge machine learning techniques.
Samal and his team surveyed 116 construction professionals, ranging from junior to senior management, across various sectors like building construction, roadworks, and industrial structures. Their goal? To pinpoint the root causes of C&D waste and identify effective minimization strategies. The results were eye-opening. “Human skill and quality control emerged as the most critical factors in reducing waste for materials like concrete, mortar, bricks, steel, and tiles,” Samal explains. “For excavated soil, proper planning was key, while quality sourcing was paramount for wood.”
But what sets this study apart is its integration of machine learning. The team tested several models, with Random Forest coming out on top, boasting an impressive R² value of 0.62. This model provided valuable insights into the relative importance of different waste minimization strategies, enhancing the robustness of the findings.
The implications for the construction industry are substantial. By adopting targeted strategies like workforce training, strict quality checks, improved planning, and prefabrication, companies can significantly reduce waste, leading to cost savings and enhanced sustainability. “This research offers a comprehensive framework for minimizing C&D waste,” Samal notes. “It’s a win-win for both the environment and the bottom line.”
However, the study is not without its limitations. Relying on self-reported survey data can introduce subjectivity and regional bias. Moreover, the results may not fully generalize beyond the Indian construction context due to the sample size and sectoral skew. The absence of real-time site data and limited access to integrated waste management systems also pose challenges.
Yet, the potential of this research to shape future developments in the field is undeniable. By combining industry perception with robust data-driven techniques, Samal and his team have paved the way for more sustainable construction management practices. As the industry continues to grapple with the challenges of urbanization and material-intensive practices, this study offers a beacon of hope, guiding the way towards a more efficient and sustainable future.