From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction

Anqi Liu; Jiangtao Zhao; Guiyuan Jiang; Feng Hong; Yanwei Yu; Bin Wang

cs.LGApr 13, 2026

From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction

Authors: Anqi Liu, Jiangtao Zhao, Guiyuan Jiang, Feng Hong, Yanwei Yu, Bin Wang

Organizations: Ocean University of China

Abstract

Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on time series-based forecasting paradigms, which inherently overlook critical aircraft state information, such as real-time kinematics and proximity to airspace boundaries. To address this limitation, we propose AeroSense, a direct state-to-flow modeling framework for air traffic prediction. Unlike classical time series-based methods that first aggregate aircraft trajectories into macroscopic flow sequences before modeling, AeroSense explicitly represents the real-time airspace situation as a dynamic set of aircraft states, enabling the direct processing of a variable number of aircraft instead of time series as inputs. Specifically, we introduce a situation-aware state representation that enables AeroSense to sense the instantaneous terminal airspace situation directly from microscopic aircraft states. Furthermore, we design a model architecture that incorporates masked self-attention to capture inter-aircraft interactions, together with two decoupled prediction heads to model heterogeneous flow dynamics across two key functional areas of the TA. Extensive experiments on a large-scale real-world airport dataset demonstrate that AeroSense consistently achieves state-of-the-art performance, validating that direct modeling of microscopic aircraft states yields substantially higher predictive fidelity than time series-based baselines. Moreover, the proposed framework exhibits superior robustness during peak traffic periods, achieves Pareto-optimal performance under dayparting multi-object evaluation, and provides meaningful interpretability through attention-based visualizations.

Figures & tables

Figure 1. Paradigm comparison for air traffic flow prediction. The proposed situation-aware paradigm directly models airspace situation for flow prediction using only instantaneous states at time $t$ , without requiring a look-back window hyperparameter.

Figure 2. Overview of the AeroSense architecture. This figure illustrates the key variables and computational steps of the inference pipeline, corresponding to Equations 10 – 26 .

Model	AP Area			AR Area
Model	MAE	RMSE	R 2	MAE	RMSE	R 2
Autoformer
w Time Embedding	2.052	2.668	0.898	4.361	5.572	0.943
w/o Time Embedding	2.048	2.603	0.903	4.238	5.624	0.942
Fedformer
w time embedding	1.872	2.404	0.917	3.170	4.078	0.969

Table 1. Performance comparison with state-of-the-art time series baselines.

Effect of Module Design
Variant	AP Area			AR Area
Variant	MAE	RMSE	R 2	MAE	RMSE	R 2
AeroSense	1.506	2.040	0.935	2.100	2.806	0.984
w/o Masked Attention	1.567	2.109	0.931	2.149	2.865	0.983
w/o Decoupled Prediction Heads	1.552	2.093	0.932	2.183	2.921	0.983
Effect of Situation-aware State Representation

Table 2. Ablation study results of AeroSense. w/o denotes the removal of a specific module.

Figure 4. Temporal distribution of prediction error (MAE) over a 24-hour cycle under dayparting evaluation. AeroSense maintains lower errors than time-series baselines across all time intervals, with particularly strong robustness during peak traffic periods.

Figure 5. Visualization of Situation-Aware Representation. Spatial attention weights for the same traffic situation at time $t$ under (a) AR and (b) AP flow prediction tasks (darker colors indicate higher importance). The aircraft marked by Arrow 2 receives high attention for AR prediction but is suppressed for AP prediction, reflecting task-specific adaptation. In contrast, the aircraft marked by Arrow 1 remains consistently down-weighted in both cases, indicating effective noise suppression. These patterns demonstrate that AeroSense dynamically decouples traffic relevance based on task-dependent kinematic constraints.

Figure 6. Visualization of the Inter-Aircraft Attention Matrix. The axes correspond to the aircraft indices within the input set. The heatmap depicts the attention weights, indicating the potential influence of the source aircraft ( $x$ -axis) on the receiver aircraft ( $y$ -axis).

Explore similar work

May 11, 2026

Unlocking air traffic flow prediction through microscopic aircraft-state modeling

Short-term air traffic flow prediction in terminal airspace is essential for proactive air traffic management. Existing approaches predominantly model traffic flow as aggregated time series. However, traffic dynamics are governed by aircraft states and their interactions in continuous airspace. Such aggregation obscures fine-grained information, including aircraft kinematics, boundary interactions, and control intent. Here we present AeroSense, a state-to-flow modeling paradigm that predicts future traffic flow directly from instantaneous airspace situations represented as dynamic sets of aircraft states derived from ADS-B trajectories. By establishing an end-to-end mapping from microscopic aircraft states to future regional traffic flow, AeroSense preserves aircraft-level dynamics while naturally accommodating varying traffic density without relying on historical look-back windows. Experiments on a large-scale real-world dataset show that AeroSense exhibits admirable predictive accuracy and robustness over aggregation-based forecasting approaches, particularly during high-density traffic periods. These findings suggest that aircraft-state situation modeling provides a promising alternative to conventional time-series forecasting in air traffic flow management.

Bin Wang, Anqi Liu, Jiangtao Zhao +8

Faculty of Information Science and Engineering, Ocean University of China, Qingdao, 266100, Shandong, China. · Sanya Oceanographic Institution, Ocean University of China, Sanya, 572022, Hainan, China. · Joint Laboratory of Data Science and Business Intelligence, Southwestern University of Finance and Economics, Chengdu, 610000, Sichuan, China. +2

Air Traffic Management Intelligent Transportation Systems Traffic Forecasting

Ask PDF

Sep 15, 2026

FlowATC: Aircraft Trajectory Prediction via Flow Matching

Building accurate decision-support tools for next-generation air traffic control requires robust trajectory prediction models. We present a flow-matching architecture trained exclusively on historical aircraft trajectories, with no route labels or chart supervision. Trained on 1.15 million Automatic Dependent Surveillance-Broadcast trajectory windows collected over the San Francisco Bay Area, the model generates aircraft trajectory distributions that closely match historical traffic, reproducing known airspace structure around San Francisco Airport such as the shape of SFO's published NIITE FOUR departure procedure. Our model is trained directly on the native, irregular ADS-B sampling interval. Trajectory prediction is cast as sequence inpainting using a block-causal Transformer that denoises future state tokens conditioned on the observed history using Conditional Flow Matching or Denoising Diffusion Probabilistic Models. We compare our architecture against constant-velocity, deterministic-Long Short Term Memory, and Conditional Variational Autoencoders baselines. At matched parameter count, CFM outperforms DDPM by 11-26% in minADE@20, and both generative objectives surpass the CVAE baseline by 31-41%. We further show that the error degrades gracefully with prediction horizon, and the architecture remains effective when retrained on temporally decimated feeds. Lastly, we sample

K

independent completions, yielding spatial probabilistic occupancy estimates that can serve as input to downstream conflict-risk estimation.

Mathurin Petit, Emir Torun, Louis Brusset +2

École Polytechnique, Palaiseau, 91128, France · Technische Universität Berlin, Berlin, 10623, Germany · Mines Paris–PSL University, Paris, 75006, France +2

Flow Matching Air Traffic Management Flow-Based Generative Modeling Trajectory Prediction Diffusion Models

Ask PDF

Mar 17, 2026

ASCENT: Transformer-Based Aircraft Trajectory Prediction in Non-Towered Terminal Airspace

Accurate trajectory prediction can improve General Aviation safety in non-towered terminal airspace, where high traffic density increases accident risk. We present ASCENT, a lightweight transformer-based model for multi-modal 3D aircraft trajectory forecasting, which integrates domain-aware 3D coordinate normalization and parameterized predictions. ASCENT employs a transformer-based motion encoder and a query-based decoder, enabling the generation of diverse maneuver hypotheses with low latency. Experiments on the TrajAir and TartanAviation datasets demonstrate that our model outperforms prior baselines, as the encoder effectively captures motion dynamics and the decoder aligns with structured aircraft traffic patterns. Furthermore, ablation studies confirm the contributions of the decoder design, coordinate-frame modeling, and parameterized outputs. These results establish ASCENT as an effective approach for real-time aircraft trajectory prediction in non-towered terminal airspace.

Alexander Prutsch, David Schinagl, Horst Possegger

Institute of Visual Computing, Graz University of Technology, Austria

Trajectory Prediction Multimodal Trajectory Prediction Air Traffic Management Transformer

Ask PDF