top of page
Previous
Antonio Torija Martinez_photo.jpg

Fateme Baneshi

University Carlos III of Madrid (UC3M), RefMap

Aviation contributes to human-induced climate change through the emission of carbon dioxide (CO2) and other non-CO2 forcing agents. The latter, responsible for roughly two-thirds of aviation’s climate effects, is highly sensitive to the time and location of emissions. Consequently, climate-aware flight planning emerges as a potential measure to mitigate its associated climate impacts. However, optimizing individual flight trajectories to reroute regions with high climate impact leads to traffic redistribution; sectors associated with warming effects tend to experience reduced traffic flow, while adjacent areas often face increased traffic density. This redistribution can introduce challenges to the manageability of the traffic, potentially raising concerns about the feasibility of such routing strategies.


This work presents a fast‑time, scalable framework built on constrained multi‑agent reinforcement learning to plan operationally feasible climate-friendly routes from the perspective of the air traffic management system. To mitigate climate impact, we identify specific airspace regions where aircraft emissions have significant warming effects, referred to as climate hotspot areas, and incorporate them as constraints that aircraft should avoid. To ensure operational feasibility of trajectories, traffic complexity is considered as the objective function to be minimized. Starting from business-as-usual trajectories, each aircraft adjusts its flight path to avoid climate hotspot areas while minimizing the overall air traffic complexity. The proposed method employs the multi-agent proximal policy optimization algorithm and adapts it to handle constraints related to climate hotspot avoidance using the Lagrangian technique. To ensure scalability, parameter sharing is employed, allowing the algorithm to deal with varying numbers of concurrently operating aircraft in different scenarios.


The effectiveness of the proposed framework is validated through an experiment using real traffic data within European airspace on December 20, 2018, encompassing all the flights operating between 12:00 UTC and 16:00 UTC. The results demonstrated that the proposed approach balances environmental objectives with air traffic manageability, achieving a 9.14% reduction in net climate effect and a 5.27% decrease in traffic complexity, with a 0.64% increase in operational cost compared to business-as-usual trajectories.

Panel Discussion

Showcasing Digital Leadership

Aircraft Trajectory Planning for Climate Impact Mitigation Considering Air Traffic Complexity: A Constrained Multi-Agent Reinforcement Learning Approach

Short Bio

Fateme Baneshi is a Ph.D. candidate in the Department of Aerospace Engineering at Universidad Carlos III de Madrid, Spain. She obtained her B.Sc. and M.Sc. degrees in Control Engineering in 2018 and 2021, respectively, graduating as the first-ranked student in both programs. Her research focuses on aircraft trajectory optimization, reinforcement learning, climate change, ATM research, and control theory and applications.


Fateme has contributed to European research projects such as RefMAP. Throughout her academic career, she has presented her work at numerous national and international conferences and published six articles in reputable, high-impact journals. Her excellence has been recognized through several prestigious awards, notably the Luis Azcárraga Aeronautical Innovation Award in 2023 and the Best Paper Award at the International Conference on Research in Air Transportation (ICRAT 2022).

Subscribe on LinkedIn to receive all the updates on our activities

horizontal_REFMAP_FINAL_LOGO-blue.png

Osquars backe 8114 28 Stockholm, Sweden

Dissemination e-mail:

refmap@futureneeds.eu

Coordination e-mail: gzampino@kth.se

  • LinkedIn
  • bluesky logo
  • X
  • Youtube
EN-Funded by the EU-POS.png

This Project has received funding from the European Union’s HORIZON Research and Innovation Programme under Grant Agreement number 101096698

© RefMap All rights reserved

Designed by Future Needs | Privacy Policy | Terms of Use

bottom of page