arXiv：cs.LG· Taeyoung Yu, Seonbin Jo, Jiwon Kim, Junyoung Byun·· 11 小时前
SeoulMMOD：首尔全市多模态 OD 流量大规模基准发布
SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
AI 导读
SeoulMMOD 是面向首尔全市多模态出行的公开基准，提供 3 年逐小时 OD 流量，覆盖 6 种出行方式、25 个区与 426 个街道，并附带出行时间、距离、日历、降雨和 POI 信号。团队用统一协议评测了 14 个预测基线，发现部分在区级有效的时空模型无法扩展到街道级 OD 预测，简单的多模态联合训练也未稳定提升精度。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.13730 [cs.LG] |
| (or arXiv:2610.13730v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13730 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Taeyoung Yu [view email]
[v1]
Fri, 9 Oct 2026 15:27:32 UTC (5,948 KB)
来源：arXiv：cs.LG · arxiv.org