arXiv subjects

Jiangtao Zhao

Publications and source records attributed to Jiangtao Zhao.

5 recordsLinked to original sources

arXiv2026

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 cues. 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, and avoids reliance on historical look-back windows. Experiments on a large-scale real-world dataset show that AeroSense exhibits strong predictive accuracy and robustness compared with time series-based forecasting approaches, without requiring exhaustive hyperparameter tuning. These findings suggest that aircraft-state situation modeling provides a promising alternative to conventional time-series forecasting in air traffic flow management.

cs.LG↗

arXiv2026

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

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 \textit{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 \textit{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.

cs.LG↗

arXiv2025

Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training

A Retrieval-Augmented Generation (RAG)-based question-answering (QA) system enhances a large language model's knowledge by retrieving relevant documents based on user queries. Discrepancies between user queries and document phrasings often necessitate query rewriting. However, in specialized domains, the rewriter model may struggle due to limited domain-specific knowledge. To resolve this, we propose the R\&R (Read the doc before Rewriting) rewriter, which involves continual pre-training on professional documents, akin to how students prepare for open-book exams by reviewing textbooks. Additionally, it can be combined with supervised fine-tuning for improved results. Experiments on multiple datasets demonstrate that R\&R excels in professional QA across multiple domains, effectively bridging the query-document gap, while maintaining good performance in general scenarios, thus advancing the application of RAG-based QA systems in specialized fields.

cs.IR↗

arXiv2023

Bragg Coherent Modulation Imaging for Highly Strained Nanocrystals-A Numerical Study

Bragg coherent diffraction imaging (BCDI) is a unique and powerful method for tracking three-dimensional strain fields non-destructively. While BCDI has been successfully applied to many scientific research fields and receives high demands, the reconstructed results for highly strained crystals are still subject to big uncertainties. Here, the progress in improving the suitability of BCDI for general samples by exploiting wavefront modulation is reported. Extensive numerical simulations demonstrate that significant improvements over the current method for reconstructing highly strained model nanocrystals can be achieved. The proposed method highly suppresses the appearance of ambiguous solutions and exhibits fast convergence and high robustness in phase retrieval. Possible experimental difficulties in implementing this method are discussed in detail.

physics.app-ph↗

arXiv2021

Revealing the three-component structure of water with principal component analysis (PCA) on X-ray spectrum

Combining the principal component analysis (PCA) of X-ray spectrum with MD simulations, we experimentally reveal the existence of three basic components in water. These components exhibit distinct structures, densities, and temperature dependencies. Among the three, two major components correspond to the low-density liquid (LDL) and the high-density liquid (HDL) predicted by the two-component model, and the third component exhibits a unique 5-hydrogen-bond configuration with an ultra-high local density. As the temperature increases, the LDL component decreases and the HDL component increases, while the third component varies non-monotonically with a peak around 20 $^{\circ}$C to 30 $^{\circ}$C. The 3D structure of the third component is further illustrated as the uniform distribution of five hydrogen-bonded neighbors on a spherical surface. Our study reveals experimental evidence for water's unique three-component structure, which provides a fundamental basis for understanding water's special properties and anomalies.

cond-mat.soft↗