Supply Chain Optimization
Lufthansa Group wanted to measure and reduce onboard food waste and improve catering loading decisions by understanding what meals passengers actually consume on different flights, routes, classes, and meal concepts.
Reported impact
Lufthansa Group uses the solution to reduce onboard food waste, optimize portion sizes and meal selection, improve loading decisions, and reduce weight-related CO2 emissions by avoiding overloading and transporting less unused food.
Lufthansa Group built Tray Tracker as an in-house AI system for catering analytics and waste reduction. At the dishwashing line after flights, the mobile Tray Tracker device scans returned meal trays from onboard catering. Its AI classifies each meal as partially eaten, completely eaten, or untouched, then combines those observations with operational context including flight route, travel class, and meal concept. The Lufthansa Group Digital Catering Analytics Team developed the system with subsidiary zeroG so catering planners can use the resulting analysis to refine portion sizes and meal selection. Lufthansa has operated the solution in Frankfurt and expanded it to Munich, with broader rollout planned across other group locations and airlines. In parallel, the Pendle machine-learning project analyzes flight duration, route, and previous demand to optimize loading before departure. Lufthansa says the long-term goal is to connect Pendle's demand analysis with Tray Tracker's post-flight consumption signals to continuously improve catering loads, reduce waste, lower transported weight, and cut related CO2 emissions.
Returned meal trays from onboard catering are scanned by Tray Tracker at the dishwashing line, where AI labels meals as partially eaten, fully eaten, or untouched. Those results are analyzed with flight route, travel class, and meal concept data to guide portion and menu decisions. Separately, Pendle uses flight duration, route, and previous demand data to optimize loading, with Lufthansa aiming to link both projects over time.
"Artificial intelligence recognizes whether a meal has been partially eaten, completely eaten, or left untouched."
"Launched by the Lufthansa Innovation Hub in 2024, the initiative uses algorithms that analyze data points such as flight duration, flight route, and previous demand to optimize loading."
"Long-term, the aim is to link the two projects."
"The flight route, travel class, and meal concept are also included in the analysis."
"The mobile technology scans meal returns from the onboard catering of flights at the dishwashing line."
"With the 'Tray Tracker,' the Lufthansa Group has developed an innovative, AI-supported solution to measure and reduce onboard meal returns."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Sep 22, 2026 Repsol Repsol needed to anticipate service-station store demand, reduce stock-outs and waste, and cut manual delivery-note entry so station teams could spend more time on customer service. A total of 85% of recommendations are accepted unchanged, and an additional 14% are accepted with quantity… Automatic delivery note reading · Suggested ordering In-house Sample Aug 13, 2026 Lockheed Martin Static flight-hour tables and usage metrics ignored real-time consumption, causing chronic under-resourcing, limited stock effectiveness, and a reactive sustainment supply chain that could not keep pace with modern… predict component failure up to 72 hours before it occurs LogC2 dashboard · deep-learning models · digital data fabric In-house Sample Est. · Jul 10, 2026 Aramco Aramco needs to turn extremely large and complex exploration, drilling, refining, logistics, and market datasets into faster, safer, and more reliable operational decisions while reducing uncertainty, downtime, and risk… five facilities recognized by the World Economic Forum as Lighthouse sites Dammam-7 · Ghawar-1 · Operations Co-Pilot 