Smart Cities and Green Energy: Integrating Civil Engineering, AI, and Environmental Policy

Abstract

This study looks into how combining civil engineering, AI, and environmental policy can aid in developing smart cities that depend on green power. A number of researchers assess whether Support Vector Machines (SVM), Random Forest (RF), Neural Networks (NN), and Gradient Boosting (GB) would be good for improving energy usage, building strong infrastructure, and assisting the environment. Gradient Boosting, based on the experiments, reached an accuracy level of 92.4% for predicting energy demand, which was more accurate than Neural Networks’ 90.1%, Random Forest’s 88.7%, and SVM’s 85.3%. GB’s approach cut carbon emissions by 18% better than NN, and NN better than RF, by 3%. The use of AI by civil engineers and policy makers results in cities being quicker to respond and better for the environment and infrastructure. Examining similar models has shown that the framework better predicts outcomes and uses less energy. Combining several fields, it addresses big challenges in cities by streamlining energy use, dealing with existing problems early, and making better decisions in policy making. Many useful tips for future smart cities are included in the study.