Aging Aircraft and Emissions: Machine Learning Predictions in Takeoff and Landing Operations

Abstract

The aviation industry plays a crucial role in global connectivity and transportation; however, its environmental footprint continues to grow alongside the expanding popularity of aviation. By analyzing a decade-long dataset, the novelty of this research lies in delving into the relationship between aircraft age and major aviation emissions, such as hydrocarbons (HC), carbon monoxide (CO), and nitrogen oxides (NOx), during landing and take-off (LTO) operation using advanced machine learning algorithms. The analysis of this research comprises three horizons. Firstly, an inventory of aircraft emissions was constructed by analyzing aircraft fleet data at Queen Alia International Airport (QAIA) in Jordan. Secondly, the correlation between these emissions and aircraft age was rigorously examined. Finally, predictive models for aircraft age based on pollutant emission features using advanced machine learning algorithms were developed. The findings of the study revealed a discernible impact of aircraft age on emissions, underscoring the importance of considering the aging factor in assessing the environmental implications of aviation. The machine learning models exhibited a capacity to forecast pollutant emissions with a notable degree of accuracy with a Mean Squared Error (MSE) of about 3.0931. This offers valuable perspectives that can enhance comprehension of aviation's environmental footprint.