OAR@UM Community:

Real-time validation of an AI-based solution for tactical air traffic complexity prediction and resolution

2026-01-09T10:12:50Z

Title: Real-time validation of an AI-based solution for tactical air traffic complexity prediction and resolution Authors: Gauci, Jason; Koopman, Cynthia; Grech, Leander; Bezzina, Maximilian; Borovich, Nicolas; Jurvansuu, Mikko; Landreville, Richard; Brambati, Francois; Vaiopoulos, Paris; Vendruscolo, Tommaso; Groia, Marianna; Berling, Didier; de Bortoli, Anthony; Giraud, Aurélien; Halladjian, Garabed; Mareschal, Louis; Vauclair, Sébastien; Charreyre, Jerôme; Zaidan, Rémi Abstract: This paper presents the real-time human-in-the-loop validation of ASTRA, an AI-based solution designed to predict and resolve 4D Areas of Relatively High ATC Complexity (4DARHACs) in congested, en-route airspace. Developed within the SESAR framework, ASTRA forecasts complex traffic events up to one hour in advance and proposes resolution strategies using flight level, speed and lateral clearances. A series of real-time simulations with Flow Management Position (FMP) operators, Air Traffic Control Officers (ATCOs) and ATCO supervisors evaluated the solution’s operational feasibility, human performance impact, and effects on capacity, efficiency, environmental performance, and safety. The results demonstrate ASTRA’s ability to predict and resolve 4DARHACs, and show that its recommended solutions reduce ATCO workload, increase en-route capacity and safety and, in most cases, lower fuel burn and CO2 emissions. The participants positively assessed the HMI and concept, while identifying integration, coordination, and scenario-realism improvements as key areas for future development.

A machine learning framework for predicting and resolving complex tactical air traffic events using historical data

2026-01-07T12:40:28Z

Title: A machine learning framework for predicting and resolving complex tactical air traffic events using historical data Authors: De Bortoli, Anthony; Koopman, Cynthia; Grech, Leander; Zaidan, Remi; Berling, Didier; Gauci, Jason Abstract: One of the key functions of Air Traffic Management (ATM) is to balance airspace capacity and demand. Despite measures that are taken during the strategic and pre-tactical phases of flight, demand–capacity imbalances still occur in flight, often manifesting as localised regions of high traffic complexity, known as hotspots. These hotspots emerge dynamically, leaving air traffic controllers with limited anticipation time and increased workload. This paper proposes a Machine Learning (ML) framework for the prediction and resolution of hotspots in congested en-route airspace up to an hour in advance. For hotspot prediction, the proposed framework integrates trajectory prediction, spatial clustering, and complexity assessment. The novelty lies in shifting complexity assessment from a sector-level perspective to the level of individual hotspots, whose complexity is quantified using a set of normalised, sector-relative metrics derived from historical data. For hotspot resolution, a Reinforcement Learning (RL) approach, based on Proximal Policy Optimisation (PPO) and a novel neural network architecture, is employed to act on airborne flights. Three single-clearance type agents—a speed agent, a flight-level agent, and a direct routing agent—and a multi-clearance type agent are trained and evaluated on thousands of historical hotspot scenarios. Results demonstrate the suitability of the proposed framework and show that hotspots are strongly seasonal and mainly occur along traffic routes. Furthermore, it is shown that RL agent performance tends to degrade with hotspot complexity in terms of certain performance metrics but remains the same, or even improves, in terms of others. The multi-clearance type agent solves the highest percentage of hotspots; however, the FL agent achieves the best overall performance.

An endurance equation for hybrid-electric aircraft

2025-09-12T08:33:56Z

Title: An endurance equation for hybrid-electric aircraft Authors: Batra, Aman; Raute, Reiko; Camilleri, Robert Abstract: This paper introduces a new endurance equation for a hybrid-electric aircraft. This research follows the derivation of a range equation for a hybrid-electric aircraft case using constant power split that was carried out by authors in their earlier work. Thus, the derivation of the endurance equation maintains the use of efficiency-based degree of hybridization (φ) used in the earlier research. For coherence, the paper also uses the same case study to assess endurance values over a range of battery energy density values and degree of hybridization (φ) values. Results show that any aircraft design has an Energy Density Threshold (EDT) value, before which the endurance of the aircraft reduces with an increase in the degree of hybridization values. Conversely, once EDT is exceeded, the endurance of the aircraft enhances with the increase in the degree of hybridization values. The EDT values are specific to the aircraft type, its specifications and key design parameters.

Rest-frame UV colors for faint galaxies at z ∼ 9–16 with the JWST NGDEEP survey

2025-07-28T09:08:15Z

Title: Rest-frame UV colors for faint galaxies at z ∼ 9–16 with the JWST NGDEEP survey Authors: Morales, Alexa M.; Finkelstein, Steven L.; Leung, Gene C. K.; Bagley, Micaela B.; Cleri, Nikko J.; Dave, Romeel; Dickinson, Mark; Ferguson, Henry C.; Hathi, Nimish P.; Jones, Ewan; Koekemoer, Anton M.; Papovich, Casey; Pérez-González, Pablo G.; Pirzkal, Nor; Smith, Britton; Wilkins, Stephen M.; Yung, L. Y. Aaron Abstract: We present measurements of the rest-frame UV spectral slope, β, for a sample of 36 faint star-forming galaxies at z ∼ 9–16 discovered in one of the deepest JWST NIRCam surveys to date, the Next Generation Deep Extragalactic Exploratory Public Survey. We use robust photometric measurements for UV-faint galaxies (down to MUV ∼ −16), originally published in Leung et al., and measure values of the UV spectral slope via photometric power-law fitting to both the observed photometry and stellar population models obtained through spectral energy distribution (SED) fitting with Bagpipes. We obtain a median and 68% confidence interval for β from photometric power-law fitting of and from SED fitting, for the full sample. We show that when only two to three photometric detections are available, SED fitting has a lower scatter and reduced biases than photometric power-law fitting. We quantify this bias and find that after correction the median . We measure physical properties for our galaxies with Bagpipes and find that our faint ( ) sample is low in mass ( ), fairly dust-poor ( mag), and modestly young ( yr) with a median star formation rate of . We find no strong evidence for ultrablue UV spectral slopes (β ∼ −3) within our sample, as would be expected for exotically metal-poor (Z/Z⊙ < 10−3) stellar populations with very high Lyman continuum escape fractions. Our observations are consistent with model predictions that galaxies of these stellar masses at z ∼ 9–16 should have only modestly low metallicities (Z/Z⊙ ∼ 0.1–0.2).