Green Costs for Hybrid Artificial Intelligence to Achieving Environmental Sustainability

Abstract

This research aims to develop a scientific framework for estimating green costs in industrial companies using hybrid artificial intelligence techniques. This framework seeks to enhance the accuracy of cost measurement and improve performance and decision-making, thereby achieving environmental sustainability. This is particularly relevant given the weakness in identifying and measuring indirect costs related to emissions, pollution, and resource consumption. These costs are often estimated and inaccurate within cost accounting systems. Therefore, this research proposes integrating hybrid artificial intelligence tools into environmental and production data analysis processes. This integration allows for the estimation of green costs at the activity and operational process levels. The research employs an analytical and applied methodology, developing a statistical model that utilizes machine learning algorithms and multi-layered neural networks to estimate green costs in the industrial environment. The results demonstrate that relying on hybrid artificial intelligence significantly improves the accuracy of cost estimation compared to traditional methods. Furthermore, it enhances management's ability to assess the environmental impact of its operational activities and make more sustainable investment decisions. The results also indicate that Integrating hybrid artificial intelligence into cost accounting systems represents a strategic step towards achieving environmental sustainability, reducing resource waste, and balancing economic efficiency with environmental responsibility.