Construction of low carbon city economic security management system based on BP artificial neural network

Abstract

Cities produce large amounts of carbon dioxide emissions, a significant factor in the severe climate problem. A small number of techniques were launched in local regions across the globe to solve the issue. The techniques were quite helpful to encourage the growth of Low-Carbon Cities (LCC). As a result, an experimental method was created in assisting decision-making in choosing the optimum practices based on the impact characteristics of carbon dioxide emissions and urban context characteristics. Therefore, it is essential to look into the inherent linkages among context characteristics and carbon emission effect characteristics. The city’s economic security is enhanced using the Back Propagation Artificial Neural Network (BP-ANN). A Low Carbon City Security Management System (LCC-SMS) is proposed in this research to enhance economic security and analyse the LCC of different cities. The mathematical model, along with the evaluation and experimental model, ensures the higher safety of the system. This study offers thinking processes in particular cities to choose the optimum solutions as models for LCC planning. The four essential parts in the suggested methodology are storage, retrieving, and adaptation and retention. This research selected two elements to characterise and depict cities: the city background features and the effect characteristics of carbon dioxide emissions. The software outcomes ensure the higher safety and performance of the proposed system.