Jul 2026· ISPRS International Journal of Geo-Information· 0 citations· 35 references
TL;DR
A Tensor Network Extended Kalman Filter (TNEKF) framework for short-term metro OD demand forecasting that consistently outperforms ARIMA, conventional EKF, and several state-of-the-art spatiotemporal prediction models in terms of MAE, RMSE, and MAPE.
Abstract
Accurate short-term metro origin–destination (OD) demand forecasting is essential for intelligent passenger flow management and urban rail transit operation. However, forecasting large-scale metro OD demand remains challenging due to its high dimensionality, nonlinear spatiotemporal dependencies, and demand uncertainty. To address these challenges, this paper proposes a Tensor Network Extended Kalman Filter (TNEKF) framework for short-term metro OD demand forecasting. First, metro OD demand is formulated as a nonlinear dynamic state-space prediction problem, where a multi-input multi-output Volterra model is adopted to characterize the nonlinear relationship between historical passenger demand and future OD flows. An Extended Kalman Filter (EKF) is then developed to recursively estimate the latent model parameters and continuously refine demand prediction using newly available observations. To improve computational efficiency for high-dimensional OD systems, both the latent state vector and covariance matrix are represented using low-rank tensor network structures, and all recursive filtering operations are implemented through tensor-network contractions without explicitly constructing large-scale matrices. Experiments on real-world smart-card data from the Hangzhou metro system demonstrate that the proposed method consistently outperforms ARIMA, conventional EKF, and several state-of-the-art spatiotemporal prediction models in terms of MAE, RMSE, and MAPE. Compared with the best-performing baseline of the whole-day scenario, the proposed method reduces MAE, RMSE, and MAPE by 30.2%, 9.8%, and 6.3%, respectively. Furthermore, the proposed framework exhibits strong robustness under disruption scenarios, demonstrating its effectiveness and scalability for large-scale metro OD demand forecasting.
A novel spatiotemporal Kalman filter network (ST-KFNet) framework for metro demand forecasting by integrating an autoregressive integrated moving average module, a Kalman filter (KF) module, and a convolutional neural network (CNN)-based variational autoencoder (VAE) module is proposed.
Ajing Su, Bing Wu, Xiaoxing Fang· Journal of Transportation En...· 0 citations
For urban ride-hailing services, accurate shortterm demand forecasting is essential for improving vehicle dispatching efficiency, reducing passenger waiting times, and supporting sustainable and intelligent urban mobility management. Short-term ride-hailing demand is shaped by complex couplings among historical demand, temporal regularity, and weather, which makes accurate prediction challenging. Unlike most existing ride-hailing forecasters that rely on graph-intensive or task-specific architectures, this paper proposes a concise Transformer-based method whose unique contribution to ridehailing demand prediction lies in two aspects: (i) a compact multifactor feature set tailored to short-term ride-hailing fluctuation, integrating historical demand, fine-grained temporal attributes, and weather variables; and (ii) explicit modelling of the nonlinear and non-monotonic effects of extreme weather and rainfall intensity on demand within a single Transformer encoder. Experiments on the City of Chicago Transportation Network Providers (TNP) dataset show that the proposed method achieves an MAE of 14.8, an RMSE of 20.1, and a MAPE of 12.1%, outperforming LSTM, Bi-LSTM, and GRU on all three metrics, with relative reductions of 20.9% in MAE, 19.3% in RMSE, and 23.4% in MAPE versus LSTM. These results demonstrate that a concise Transformer with carefully designed multi-factor features can serve as an effective, reproducible baseline for short-term ridehailing demand forecasting, supporting smarter vehicle allocation, lower idle mileage, and reduced energy consumption and carbon emissions in intelligent transportation systems.
Yuanzhe Liu· 2026 2nd International Confe...· 0 citations
: Accurate short-term taxi demand forecasting is essential for efficient urban transportation, as it directly influences fleet allocation, passenger waiting times, and quality of service. This work studies multi-horizon taxi demand prediction as the task of learning a mapping from past observations to multiple future demand values under temporal dependence and uncertainty. A data-driven framework is developed using data from the New York City Taxi and Limousine Commission, where raw trip records are transformed into structured temporal representations through lag-based features, cyclical encoding, and statistical summaries. The framework evaluates sequence modeling architectures for multi-step prediction, such as recurrent models, in particular Long Short-Term Memory (LSTM) networks, and attention-based models, i.e., Transformer architectures. Evaluation across multiple forecasting horizons reveals that attention-based models consistently achieve lower prediction error, indicating their capability to capture the long-term temporal dependencies needed to predict multiple horizons. Conformal prediction and Monte Carlo Dropout are used to produce calibrated prediction intervals and point forecasts that represent demand variability under uncertainty. The findings indicate that successful multi-horizon forecasting requires global temporal interaction and explicit quantification of uncertainty. The proposed framework provides a systematic and scalable approach for real-world deployment in intelligent transportation systems.
Magesh Rajakumar, C. Markarian, S. Atalla· Proceedings of the 15th Inte...· 0 citations
Accurate forecasting of origin-destination (O-D) demand is critical for transportation network design, planning, and operational management. An underexplored challenge is inductive forecasting: predicting O-D flows for new or unobserved locations, which is essential for evaluating network expansions and new facility placements. However, most existing approaches either are transductive (limited to fixed observed networks) or are deep learning models that lack interpretability, fail to provide uncertainty quantification, and often overlook critical data constraints such as structural zeros. To this end, we develop a Bayesian spatiotemporal hierarchical model for probabilistic O-D demand estimation, designed specifically for inductive forecasting. We assume total trip generation is given and model the destination-choice counts using a multinomial distribution. To handle the high-dimensional probability tensor, which features both simplex and structural zero constraints, we parameterize it via a masked-centered softmax transformation of a latent utility tensor. We then model this latent utility tensor using a CANDECOMP/PARAFAC (CP) tensor factorization to parsimoniously capture spatiotemporal patterns. Crucially, we impose Gaussian process (GP) priors on the spatial and temporal latent factors; the GP over the network provides the principled statistical mechanism to make inductive predictions for new locations. For posterior inference, we propose an Markov chain Monte Carlo algorithm. We validate the proposed model on synthetic data and two real-world O-D data sets. Results confirm our model’s ability to accurately estimate O-D flows and provide robust inductive forecasts with full uncertainty quantification, which is essential for robust decision making in downstream applications, such as stochastic network optimization and facility location problems.
Funding: This research is supported by the Natural Sciences and Engineering Research Council (NSERC) of Canada [Discovery Grant RGPIN-2025-04479].
Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2026.0063 .
As urban rail transit systems enter a stage of high-quality development, accurate short-term passenger flow forecasting has become essential for efficient operation and management. To improve the accuracy and robustness of multi-step short-term passenger flow forecasting under fluctuating demand conditions, this study develops a feature-enhanced Informer framework that embeds Complex Network Representation (CNR) into the Informer architecture to jointly capture both the topological characteristics of the subway network and spatiotemporal passenger flow dynamics. External factors, including subway schedules and land use around stations, are further integrated to enrich the input features. In addition, the ProbSparse self-attention mechanism is adopted to improve long-sequence dependency modeling, thereby enabling efficient multi-step passenger flow forecasting. Experiments were conducted on the Beijing metro passenger flow dataset from January to October 2024 to evaluate the proposed model. The dataset covered 264 stations and was aggregated at 15 min intervals. Based on historical passenger flow and multi-source features, the model predicts passenger flow over multiple future time steps. The overall evaluation metrics were calculated on the test set and averaged over all test samples and observed stations. The experimental results show that, compared with the standard Transformer model, the proposed model reduces the average prediction error by 16.59% on weekdays and 20.48% on weekends while maintaining stable predictive performance during peak hours. Sensitivity analysis and ablation studies are further conducted to evaluate the model performance across different station types and forecasting horizons. The results demonstrate that the proposed model can provide reliable decision support for intelligent urban rail transit operations, including transport capacity scheduling, passenger service improvement, and operating cost reduction.
Gang Li, Junfeng An, Junguo Si et al.· Vehicles· 0 citations
Short-term traffic speed forecasting based on sensor-derived traffic signals is important for route guidance, adaptive signal control, congestion management and intelligent transportation services. Accurate prediction remains challenging because urban traffic states are influenced by nonlinear temporal dynamics, inter-node relationships, heterogeneous contextual information and uncertainty in external conditions. This study proposes U-GRU, a staged forecasting model that integrates node-wise gated recurrent temporal encoding, a one-dimensional U-Net-based ordered-node feature transformation module, external-feature alignment and channel–temporal recalibration. Unlike graph-convolutional methods that explicitly propagate information through a predefined or learned road topology, U-GRU investigates whether a transformation path along the stored node order in the data files can provide a useful representation under an ordered-node assumption. POI-related and weather-related auxiliary matrices are used as external representations provided in the public dataset; because field-level semantic metadata are unavailable, they are treated as dataset-level auxiliary inputs rather than manually interpreted variables. The experiments use chronological train/validation/test splitting, validation-based checkpoint selection, five random seeds for U-GRU, an expanded baseline set including the STGformer baseline evaluated under the same SZ-taxi setting, ablation studies, weather-validity analysis and node-order sensitivity analysis. On the SZ-taxi dataset, U-GRU reports MAE values of 2.70–2.72, RMSE values of 4.04–4.12 and R2 values of 0.83–0.85 across the 15–60 min forecasting horizons. The results suggest comparable or slightly better short-term forecasting performance under the evaluated dataset and protocol, while the conclusions remain dataset-specific and should be further examined on additional traffic networks.