Contingency Fuel Prediction with Explainable Machine Learning for Airline Operations

Abstract

Aircraft carry additional fuel reserves, referred to as contingency fuel, used to account for unforeseen events during a flight. Previous research has attempted to quantify the magnitude of such events, most notably the probability of adverse weather or ATFM regulation, yet their inherent unpredictability introduces uncertainty and frequently results in the overestimation of contingency fuel requirements. Recent studies use data-driven fuel-burn predictions to better estimate contingency fuel sizing; however, most are confined to specific routes or regions, limiting generalizability. To address this, we utilise real operational airline data covering both regional and intercontinental flights, and develop a quantile regression framework for predicting contingency fuel requirements, capable of adapting to more diverse set of flight characteristics. Our framework integrates flight-plan data, TAF weather forecasts, and proxy congestion features to predict required contingency fuel at varying quantile levels, enabling trade-offs between efficiency and safety. Unlike the current Statistical Contingency Fuel process, which applies different coverage levels by risk category, this evaluation uses a single fixed quantile for all flights when generating predictions. In a four-month out-of-sample evaluation, a single fixed quantile matched the safety performance of the Statistical Contingency Fuel process while reducing excess fuel carriage by up to 235,364 kg (≈11%). A more conservative quantile configuration yielded smaller savings but reduced abnormal flight-phase events by 22.2%. The key drivers of the final predictions are evaluated, offering pilots and dispatchers transparent explanations that can build trust and reduce reliance on discretionary fuel loading.