Dams significantly impact the environment, industries, residential areas, and agriculture. Efficient dam management can mitigate negative impacts and enhance benefits such as flood and drought reduction, energy efficiency, water access, and improved irrigation. This study tackles the critical issue of predicting dam occupancy levels precisely to contribute to sustainable water management by enabling efficient water allocation among sectors, proactive drought management, controlled flood risk mitigation, and preservation of downstream ecological integrity. Our research suggests that combining physical models of water inflow and outflow “such as evapotranspiration using the Penman–Monteith equation, along with parameters like water consumption, solar radiation, and rainfall” with data-driven models based on historical reservoir data is crucial for accurately predicting occupancy levels. We implemented various prediction models, including Random Forest, Extra Trees, Long Short-Term Memory, Orthogonal Matching Pursuit CV, and Lasso Lars CV. To strengthen our proposed model with robust evidence, we conducted statistical tests on the mean absolute percentage errors of the models. Consequently, we demonstrated the impact of physical model parameters on prediction performance and identified the best method for predicting dam occupancy levels by comparing it with findings from the scientific literature.

In today’s world, energy efficiency is becoming increasingly crucial, due to its impact on sustainability in production. Designing systems that consume less energy and manage resources efficiently is essential. Variations in operating speed can affect processing time, energy consumption, idle times of subsequent machines, work delays, and missed deadlines. While most studies focus on prediction parameters like cut depth and cut area to estimate the energy consumption or processing time, our approach emphasizes variations in G-code motion parameters. To enhance both precision and the adaptability of the model to all Computer Numerical Control (CNC) machines in no-load condition, we propose an intelligent hybrid model that combines physical and data-driven approaches. The first approach employs curve fitting based on the physical model, while the second utilizes deep neural network (DNN) models optimized through hyperparameter tuning. The DNN topologies we evaluated exhibit high performance, with prediction errors of less than 1% for all models. Our approach provides a more precise and comprehensive understanding of energy consumption patterns in manufacturing processes, enabling manufacturers to make informed decisions about energy utilization, cost reduction, and sustainability. Our study aims to advance the field of energy efficiency in manufacturing and contribute to a more sustainable future.

This study explores the relationship between air quality on university campuses and the concepts of sustainable education and energy. University serves as a crucial connection between education and environmental responsibility. Air quality (AQ) not only affects the well-being of students and staff but also mirrors the environmental sustainability objectives of these institutions. The development of sensor placement strategies for measuring air pollution on campuses holds the potential to enhance environmental awareness and facilitate clean energy implementation within the concept of sustainable energy. In this study, data were obtained from sensors monitoring parameters such as temperature, humidity, CO2, AQ, and pressure within an indoor classroom. The second phase of the study was regarding the optimal number and placement of sensors within these classroom environments. Ultimately, this research lays the groundwork for educational institutions to meet their environmental and energy responsibilities while concurrently providing students with a clean and healthy environment. Request access from your librarian to read this chapter's full text.