mlsanityData to 14 Oct 2026

SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark

arXiv 2610.13730 ↗First posted 9 Oct 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Origin-destination (OD) flow forecasting supports urban mobility decisions by predicting the volume and patterns of human movement across a city. Most existing public OD benchmarks provide only a partial view of citywide mobility, covering a single transport service or at most two modes. With partial mode coverage, observed demand changes are difficult to separate into shifts across transport modes and changes in total travel. We introduce SeoulMMOD, a large-scale public benchmark for citywide multimodal mobility in Seoul. SeoulMMOD provides three years of hourly OD flows estimating total mobility for 6 urban travel modes across 25 districts and 426 sub-districts, together with travel-time, travel-distance, calendar, rainfall, and point-of-interest (POI) signals. Using SeoulMMOD, we benchmark 14 forecasting baselines under a common protocol and analyse the effects of spatial scaling, joint versus mode-separate training, and cross-year generalization. Results show that several spatio-temporal models that work at district level do not scale to sub-district OD forecasting, and that naive joint multi-mode training does not consistently improve accuracy. Together, the dataset and benchmark establish a reproducible testbed for multi-mode, multi-year OD forecasting at the city scale.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

18 of 44 references.

References · 18

  1. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  2. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  3. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  4. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  5. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  6. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  7. 2018Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Predictioncited by 122
  8. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  9. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 76
  10. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 53
  11. 2019Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Predictioncited by 35
  12. 2020Learning Geo-Contextual Embeddings for Commuting Flow Predictioncited by 28
6 more
  1. 2020Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approachcited by 16
  2. 2023An Interdisciplinary Survey on Origin-destination Flows Modeling: Theory and Techniquescited by 13
  3. 2021Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregationcited by 12
  4. 2021Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approachcited by 11
  5. 2022ODformer: Spatial-Temporal Transformers for Long Sequence Origin-Destination Matrix Forecasting Against Cross Application Scenariocited by 5
  6. 2024ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Predictioncited by 3

Built on by

Not cited yet.