Data Science to improve operations: Fuel efficiency optimization

Nowadays, as with society as a whole, aviation is aware and concerned about the environment. In a business-as-usual scenario, predicted traffic growth in this sector would lead to an increase of global emissions up to 22% by 2050. As a result, measures are being taken to mitigate these emissions. In order to respond to this traffic growth without compromising the environment, the aviation sector is making a great effort to reduce fuel consumption by maximizing its efficiency. This action will not only benefit the environment, but also economical and human scales.

Carbon dioxide is one of the gases contributing to the greenhouse effect. These gases keep the Earth warm by absorbing the sun’s energy, leading to harmful consequences with the atmosphere. Nearly 2% of carbon dioxide (CO2) emissions are produced by aviation. To mitigate this effect, significant progress is being achieved in fuel efficiency, which in turn presents both environmental and economical benefits for the airline (airlines spend approximately 25 percent of their operating costs on fuel according to IATA). 

The aviation sector is looking for new technologies, designs and materials to reduce fuel usage: improved aerodynamics (e.g. winglets to reduce drag), more efficient engines, innovative designs (e.g. Blended Wing Bodies, BWB) and/or lighter materials. There are also actual navigation systems, which help in avoiding bad weather conditions, and these devices will also diminish the usage of CO2 per flight. On that same note, working strategies such as Continuous Climb and Descendant Operations (CCO and CDO) permit aircraft to fulfill an ideal flight path (decrease in fuel burned, lowered global gas emissions, noise and fuel costs).

While much has been invested to increase flight efficiency through these aircrafts’ (already highly efficient) components and operational concepts, the emergence of big data techniques can be game-changing technology. The use of Al systems, combined with machine learning algorithms, are being used to better understand aircraft performance through its generated data. This analysis provides a rich characterization of the contributing factor on flight efficiency: route distance, altitudes, aircraft types, weight, temperature, speed, wind, weather, etc. The analysis of contributing factors (or precursors) enables an accurate prediction of the optimal amount of fuel needed for a particular flight, considering all its conditions. This predictive analysis can also be applied to effective route planning in speed and altitude as well as to lateral flight path for an optimized flight efficiency.

The combination of the highly skilled workforce available in aviation, its most advanced technologies and the smooth introduction of data-driven techniques can enable a greener aviation capable of reducing aviation’s environmental impact in support of a more environmentally-friendly society.

About Author

Lara Moro

Lara is finishing her BSc in Aerospace Engineering. Lara is eager to learn, and joins the team with broad curiosity and initiative. She loves to travel and takes advantage of every opportunity to discover new places; perhaps a reason why she has great interests in the aviation sector! Read more about Lara Moro

Related Posts