Data-Driven Assessment of Waste-to-Energy Potential for Sustainable Campus Systems: A Case Study of Shivaji University, India

Introduction: The rapid increase in solid waste generation in institutional campuses presents significant challenges in sustainable waste management, resource recovery, and energy efficiency. Conventional disposal practices such as landfilling result in environmental degradation and loss of valuable resources. Waste-to-energy (WtE) conversion offers a viable pathway to transform campus waste into useful energy while supporting circular economy principles. This study focuses on evaluating WtE potential for Shivaji University, Kolhapur, Maharashtra, as a real-case application.

Methods: A comprehensive assessment of campus waste streams, including food waste, garden biomass, paper, and plastic, was conducted. Key parameters such as waste quantity, composition, moisture content, and calorific value were analyzed to evaluate suitability for energy recovery through biogas and thermal processes. A data-driven approach was adopted using machine learning models, including Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), to predict energy generation potential. Model performance was evaluated using RMSE, MAE, and R² metrics.

Results: The findings indicate that approximately 65–75% of total campus waste can be recycled or converted into energy, resulting in a 30–40% reduction in landfill dependency. The predicted WtE potential demonstrates that 15–25% of campus energy demand can be met through waste-derived energy. Comparative analysis shows that the LSTM model achieves 20–26% lower prediction error than RF and SVM, and up to 30% improvement over LR, providing more reliable estimates than conventional methods.

Conclusions: The proposed framework demonstrates the potential of integrating recycling, waste utilization, and predictive analytics for sustainable campus management. The study highlights a scalable approach for institutional WtE systems, contributing to improved resource recovery, energy efficiency, and circular economy implementation.