Unforeseen events (e.g., COVID-19, the Russia-Ukraine conflict) create significant challenges for accurately predicting CO2 emissions in the airline industry. These events severely disrupt air travel by grounding planes and creating unpredictable, ad hoc flight schedules. This leads to many missing data points and data quality issues in the emission datasets, hampering accurate prediction. To address this issue, we develop a predictive analytics method to forecast CO2 emissions using a unique dataset of monthly emissions from 29,707 aircraft. Our approach outperforms prominent machine learning techniques in both accuracy and computational time. This paper contributes to theoretical knowledge in three ways: 1) advancing predictive analytics theory, 2) illustrating the organisational benefits of using analytics for decision-making, and 3) contributing to the growing focus on aviation in information systems literature. From a practical standpoint, our industry partner adopted our forecasting approach under an evaluation licence into their client-facing CO2 emissions platform.

不可预见的事件（例如，新冠肺炎 (COVID-19)、俄罗斯-乌克兰冲突）给准确预测航空业二氧化碳排放量带来了重大挑战。这些事件导致飞机停飞并造成不可预测的临时航班时刻表，从而严重扰乱航空旅行。这导致排放数据集中存在许多数据点缺失和数据质量问题，从而妨碍了准确的预测。为了解决这个问题，我们开发了一种预测分析方法，使用 29,707 架飞机每月排放量的独特数据集来预测二氧化碳排放量。我们的方法在准确性和计算时间方面都优于著名的机器学习技术。本文通过三种方式对理论知识做出了贡献：1）推进预测分析理论，2）说明使用分析进行决策的组织优势，3）促进信息系统文献中对航空的日益关注。从实际角度来看，我们的行业合作伙伴在评估许可下采用了我们的预测方法到他们面向客户的二氧化碳排放平台中。