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

Taeyoung Yu; Seonbin Jo; Jiwon Kim; Junyoung Byun

cs.LGOct 9, 2026

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

Authors: Taeyoung Yu, Seonbin Jo, Jiwon Kim, Junyoung Byun

Organizations: The University of Queensland · POSTECH · Chung-Ang University

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.

Figures & tables

Figure 1: Annual OD outflow in SeoulMMOD (2024) from the same Seoul origin at district and sub-district levels. Arc color indicates the destination’s dominant transport mode.

Dataset	Coverage	Modes	# Nodes	# OD pairs	Trip attrs	Context	Public
Zone-level forecasting
Liang et al. [ 11 ]	2018-03 – 2018-08	subway, ride-hailing	136 + 63	—	$\times$	$\times$	$\times$
Ke et al. [ 9 ]	2018-01 – 2018-12	solo ride-hailing, shared ride-hailing	63	—	$\times$	$\times$	$\times$
Yao et al. [ 32 ]	2015-01 – 2015-03 / 2016-07 – 2016-08	bike, taxi	200	—	$\times$	$\times$	✓
OD-level forecasting
Zhang et al. [ 34 ] (BJ)	2016-02 – 2016-04	subway, bus	276 + 2,320	28,802	$\times$	$\times$	$\times$

Table 1: Related dataset comparison. Trip attrs lists per-record auxiliary attributes (average travel time / distance). Context lists bundled signals (holiday, point-of-interest, weather). “+” denotes separate node sets for different modes.

Panel of Figure 2 — Figure 2: Aggregate and temporal characteristics of SeoulMMOD . (a) Distribution of OD-record flow. (b) Morning-rush net inflow, computed as inflow minus outflow during 07:00–09:00. (c) Hourly profile by day type. (d) Monthly trend across years.

Panel of Figure 3 — Figure 3: Multi-mode structural diversity. (a) Mode composition over the day. (b) Pairwise Pearson correlation of hourly total flow between modes. (c, d) Disparity-filtered backbone networks and Louvain communities for car and walk, with edge opacity and width proportional to flow. Additional distributional and community-similarity views are shown in Appendix A .

Panel of Figure 4 — Figure 4: Trip attributes and contextual information in SeoulMMOD . (a) District-level travel distance and travel time, with marker size showing average hourly outflow. (b) Per-mode hourly flow change under rainfall categories, relative to dry hours. (c) Hourly inflow for office and leisure destination examples on weekdays and holidays. (d) Weekday net-inflow ratio for selected office, education, and low-POI residential examples.

	6h $\to$ 6h			12h $\to$ 12h			24h $\to$ 24h			Cost (24h)
Model	MAE	RMSE	wMAPE	MAE	RMSE	wMAPE	MAE	RMSE	wMAPE	#Params	BS	Train/ep	Total
District scale (625 OD pairs)
HA	22.9	112.2	10.5%	22.9	112.2	10.5%	22.8	111.8	10.5%	—	—	—	—
LV	106.6	566.8	49.0%	144.2	692.3	66.3%	139.0	678.8	63.9%	—	—	—	—
STAEformer	21.8	93.7	10.1%	22.8	100.1	10.5%	21.4	92.9	9.8%	2.8M	8	83s	2.3h
STID	23.4	99.7	10.8%	25.1	106.9	11.5%	24.6	111.7	11.3%	143K	16	3.2s	0.09h

Table 2: Multi-horizon performance and computational cost, aggregated across modes. Bold marks the best and underline marks the second-best per (horizon, metric) within each level. Cost columns report parameter count, batch size, per-epoch wall-clock, and 100-epoch wall-clock estimates at the 24h

\to

24h horizon.

	metro bus		local bus		subway		walk		car		other		Avg
Model	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
HA	2.00	7.85	18.7	72.4	32.2	73.2	35.2	233.4	30.5	74.7	18.1	64.9	22.8	111.8
LV	6.11	34.3	104.9	417.8	231.1	466.1	232.1	1429.7	160.0	436.3	99.8	371.0	139.0	678.8
STAEformer	2.30	11.2	16.5	55.4	33.0	72.0	28.3	188.9	31.1	69.4	17.0	54.3	21.4	92.9
STID	2.94	13.9	19.4	65.2	37.4	82.7	33.1	231.7	35.3	78.9	19.6	60.9	24.6	111.7
AGCRN	2.83	13.1	21.7	79.0	45.0	103.9	53.0	401.8	38.0	89.0	21.7	73.4	30.4	178.9

Table 3: Per-mode MAE and RMSE at the 24h

\to

24h horizon, district level. Bold marks the best and underline marks the second-best per (mode, metric).

	STID			AGCRN			STAEformer			MTGNN
Mode	Joint	Sep	$\Delta$	Joint	Sep	$\Delta$	Joint	Sep	$\Delta$	Joint	Sep	$\Delta$
metro_bus	2.94	1.79	$-39.0\%$	2.83	2.05	$-27.8\%$	2.30	1.81	$-21.0\%$	3.00	1.86	$-38.1\%$
local_bus	19.36	15.85	$-18.1\%$	21.71	18.74	$-13.7\%$	16.51	16.01	$-3.0\%$	20.80	17.52	$-15.7\%$
subway	37.43	30.98	$-17.2\%$	44.98	41.17	$-8.5\%$	32.95	29.37	$-10.9\%$	44.56	34.14	$-23.4\%$
walk	33.14	27.77	$-16.2\%$	53.02	43.50	$-18.0\%$	28.33	29.80	$+5.2\%$	37.87	35.50	$-6.3\%$
car	35.32	29.38	$-16.8\%$	37.96	32.27	$-15.0\%$	31.12	27.90	$-10.3\%$	37.13	31.85	$-14.2\%$

Table 4: Joint training vs one model per mode for four spatio-temporal models at the district 24h horizon. Bold marks the lower MAE per (model, mode).

\Delta

(\mathrm{Sep}-\mathrm{Joint})/\mathrm{Joint}

Model	2024 test	2025 overall	Spring	Summer	Fall	Winter	$\Delta$
STAEformer	21.37	25.83	28.29	23.70	25.75	25.56	$+20.89\%$
AGCRN	30.37	35.77	37.33	32.84	36.93	36.00	$+17.78\%$
GWNet	27.55	33.47	35.21	30.60	33.84	34.29	$+21.49\%$
MTGNN	27.40	32.35	34.63	29.95	31.93	32.89	$+18.07\%$
iTransformer	25.33	28.08	29.87	26.65	28.35	27.42	$+10.86\%$

Table 5: Cross-year generalization at the district 24h horizon (train 2024, test 2025), broken down by season. Bold marks the easiest season per model.

\Delta\%

is the in-year vs cross-year MAE change.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 5 — Figure 5: Additional descriptive views of multi-mode OD structure. (a) Complementary cumulative distribution of OD-pair flows per mode. (b) Distribution of OD-record flow by mode. (c) Distribution of average OD-record distance by mode. (d) Normalised mutual information between per-mode community assignments.

Day type	$n$ days	Trips/day	metro bus	local bus	subway	walk	car	other
Weekday	246	20.64 M	0.61	12.48	21.73	33.06	20.66	11.45
Weekend	101	16.87 M	0.59	12.80	17.63	35.06	22.80	11.12
Holiday	19	14.71 M	0.59	12.58	16.24	36.35	23.61	10.63
Change vs weekday (pp)			metro bus	local bus	subway	walk	car	other
Weekend	—	$-$ 18%	$-$ 0.02	$+$ 0.32	$-$ 4.10	$+$ 1.99	$+$ 2.14	$-$ 0.33
Holiday	—	$-$ 29%	$-$ 0.02	$+$ 0.10	$-$ 5.50	$+$ 3.29	$+$ 2.95	$-$ 0.82

Appendix

Table 6: Mode share (%) and total daily trip volume by day type for 2024 at the district scale. Holiday counts Korean public holidays. Weekend excludes days flagged as holidays. Mode shares sum to 100% per row.

Condition	$n$ cells	Share	metro bus	local bus	subway	walk	car	other
Dry (0 mm)	206,895	94.21%	0.60	12.55	20.49	33.74	21.30	11.33
Trace ( $<$ 0.5 mm)	3,012	1.37%	0.67	12.38	21.22	32.44	21.75	11.54
Light (0.5–2 mm)	5,741	2.61%	0.63	12.74	21.09	33.13	20.98	11.43
Moderate (2–10 mm)	3,283	1.49%	0.62	13.04	20.88	32.43	21.44	11.58
Heavy ( $>$ 10 mm)	669	0.30%	0.62	13.42	22.42	30.60	21.06	11.87

Appendix

Table 7: Origin district-hour mode share (%) by rainfall intensity, district scale, 2024. Mode shares sum to 100% per row.

Group	Categories
Transport infrastructure	airport, rail station, bus terminal, subway station, bus stop
Commerce and leisure	attraction, bank, department store, supermarket, theater, hotel
Public and health services	government office, general hospital, clinic, pharmacy
Education	kindergarten, elementary school, middle school, high school, university

Appendix

Table 8: POI count features grouped into four broad groups for presentation.

POI	Mode	$r$ (count)	$r_{s}$	$r$ (density)	$r$ (partial $\|$ area)
Subway station	subway	$+$ 0.458	$+$ 0.442	$+$ 0.438	$+$ 0.475
Bank	subway	$+$ 0.356	$+$ 0.314	$+$ 0.430	$+$ 0.369
Theater	subway	$+$ 0.345	$+$ 0.298	$+$ 0.332	$+$ 0.347
Subway station	local bus	$-$ 0.284	$-$ 0.324	$-$ 0.256	$-$ 0.286
Bus stop	local bus	$+$ 0.276	$+$ 0.324	$+$ 0.318	$+$ 0.338
Kindergarten	subway	$-$ 0.283	$-$ 0.307	$-$ 0.257	$-$ 0.283

Appendix

Table 9: Correlation between per-sub-district POI count and destination mode share. We report four correlation variants per (POI, mode) pair — Pearson

r

on counts, Spearman

r_{s}

, Pearson

r

on per-km 2 density, and partial

r

controlling for sub-district area. Rows have raw

|r|{\geq}0.20

and BH-adjusted

q{<}0.001

Variant	MAE @ 6	MAE @ 12	MAE @ 24	$\Delta$ @ 6	$\Delta$ @ 12	$\Delta$ @ 24
STID base	23.41	25.07	24.63	—	—	—
+ Holiday	23.81	25.55	23.24	$+$ 0.40	$+$ 0.48	$-$ 1.39
+ POI	22.97	25.35	24.14	$-$ 0.44	$+$ 0.28	$-$ 0.49
+ Rainfall	24.75	24.37	24.14	$+$ 1.34	$-$ 0.70	$-$ 0.49

Appendix

Table 10: Test MAE on the 2024 district-scale dataset when STID is extended with each contextual signal in isolation. Lower is better, bold marks the best per horizon, and

\Delta

is the change against STID base .

Figure 6: Error stratification by destination-district POI count. (a) Districts with more POIs have larger target volume. (b) Absolute MAE increases with POI count for HA and STAEformer. (c) Relative error decreases with POI count, indicating that high-volume districts can have larger absolute errors but smaller percentage errors. Pearson correlations are shown in each panel.

Forecasting Benchmarks

Forecasting Benchmarks are datasets and evaluation protocols for comparing predictions of future time-series values, events, and outcomes.

See all 227 papers

Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting
Aug 28, 2026Yixuan Zhao, Man LuoRepresentation Learning Transfer Learning
University of Exeter Department of Computer Science Exeter, United Kingdom
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
Jul 6, 2026Zherui Huang, Guanjie Zheng, Hao Xue +1Geospatial Representation Learning Geospatial Reasoning
Shanghai Jiao Tong University · The Hong Kong University of Science and Technology (Guangzhou) · The University of New South Wales, Sydney
DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling
Jun 8, 2026Jie Zhao, Xianqi Dai, Jie Feng +2Intelligent Transportation Systems Synthetic Data Generation
Department of Electronic Engineering, BNRist, Tsinghua University · Tsinghua Shenzhen International Graduate School · Zhongguancun Academy

Aug 28, 2026J/K move · Enter open · S save

Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting

Yixuan Zhao, Man Luo

University of Exeter Department of Computer Science Exeter, United Kingdom

Representation Learning Transfer Learning Spatiotemporal Forecasting

Open paper AskPDF arXiv

Urban transportation systems consist of multiple mobility modes that coexist within the same city and exhibit complex interdependencies, leading to correlated demand dynamics across modes. However, forecasting demand jointly across different modes remains challenging due to substantial heterogeneity in space and the limited availability of historical data for emerging modes. Existing forecasting methods are largely developed for individual mobility modes and implicitly assume compatible spatial structures between source and target systems, which severely restricts their applicability in multi-modal settings. To address these challenges, we propose TransMod, a unified framework for urban mobility demand forecasting that enables effective knowledge transfer across heterogeneous mobility modes. TransMod constructs a shared zone-level spatial representation that aligns mobility systems with different spatial granularities into a common space, thereby reducing structural mismatch and distributional shift. Built on this unified representation, TransMod further learns transferable spatio-temporal patterns from data-rich source modes and adapts them to data-scarce target modes, alleviating the dependence on extensive target-domain histories. Extensive experiments on real-world datasets demonstrate that TransMod consistently outperforms existing approaches and provides robust forecasting performance under limited target data.

Abstract

Forecasting Benchmarks

Explore similar work

Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting

GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation

DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling