Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model

The origin–destination (OD) matrix describes traffic flow information between regions. It is a critical input for intelligent transportation systems (ITS). However, obtaining the OD matrix remains challenging due to high costs and privacy concerns. Synthetic data, which have the same statistical dis...

Full description

Saved in:
Bibliographic Details
Main Authors: Zehao Yuan, Xuanyan Chen, Biyu Chen, Yubo Luo, Yu Zhang, Wenxin Teng, Chao Zhang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/14/4/172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144879634546688
author Zehao Yuan
Xuanyan Chen
Biyu Chen
Yubo Luo
Yu Zhang
Wenxin Teng
Chao Zhang
author_facet Zehao Yuan
Xuanyan Chen
Biyu Chen
Yubo Luo
Yu Zhang
Wenxin Teng
Chao Zhang
author_sort Zehao Yuan
collection DOAJ
description The origin–destination (OD) matrix describes traffic flow information between regions. It is a critical input for intelligent transportation systems (ITS). However, obtaining the OD matrix remains challenging due to high costs and privacy concerns. Synthetic data, which have the same statistical distribution of real data, help address privacy issues and data scarcity. Based on Generative Adversarial Networks (GAN), OD matrix generation models, which can effectively generate a synthetic OD matrix, help to address the challenge of obtaining OD matrix data in ITS research. However, existing OD matrix generation methods can only handle with tens of nodes. To address this challenge, this study proposes the Origin–Destination Progressive Growing Generative Adversarial Networks (OD-PGGAN) for large-scale OD matrix generation task which adapt the PGGAN architecture. OD-PGGAN adopts a progressive learning strategy to gradually learn the structure of the OD matrix from a coarse to fine scale. OD-PGGAN utilizes multi-scale generators and discriminators to perform generation and discrimination tasks at different spatial resolutions. OD-PGGAN introduces a geography-based upsampling and downsampling algorithm to maintain the geographical significance of the OD matrix during spatial resolution transformations. The results demonstrate that the proposed OD-PGGAN can generate a large-scale synthetic OD matrix with 1024 nodes that have the same distribution as the real sample and outperforms two classical methods. The OD-PGGAN can effectively provide reliable synthetic data for transportation applications.
format Article
id doaj-art-6dc08fcf9f4b44d3be909f5a35a6b40e
institution OA Journals
issn 2220-9964
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj-art-6dc08fcf9f4b44d3be909f5a35a6b40e2025-08-20T02:28:14ZengMDPI AGISPRS International Journal of Geo-Information2220-99642025-04-0114417210.3390/ijgi14040172Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks ModelZehao Yuan0Xuanyan Chen1Biyu Chen2Yubo Luo3Yu Zhang4Wenxin Teng5Chao Zhang6State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaHangzhou Institute of Technology, Xidian University, Hangzhou 311200, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaThe origin–destination (OD) matrix describes traffic flow information between regions. It is a critical input for intelligent transportation systems (ITS). However, obtaining the OD matrix remains challenging due to high costs and privacy concerns. Synthetic data, which have the same statistical distribution of real data, help address privacy issues and data scarcity. Based on Generative Adversarial Networks (GAN), OD matrix generation models, which can effectively generate a synthetic OD matrix, help to address the challenge of obtaining OD matrix data in ITS research. However, existing OD matrix generation methods can only handle with tens of nodes. To address this challenge, this study proposes the Origin–Destination Progressive Growing Generative Adversarial Networks (OD-PGGAN) for large-scale OD matrix generation task which adapt the PGGAN architecture. OD-PGGAN adopts a progressive learning strategy to gradually learn the structure of the OD matrix from a coarse to fine scale. OD-PGGAN utilizes multi-scale generators and discriminators to perform generation and discrimination tasks at different spatial resolutions. OD-PGGAN introduces a geography-based upsampling and downsampling algorithm to maintain the geographical significance of the OD matrix during spatial resolution transformations. The results demonstrate that the proposed OD-PGGAN can generate a large-scale synthetic OD matrix with 1024 nodes that have the same distribution as the real sample and outperforms two classical methods. The OD-PGGAN can effectively provide reliable synthetic data for transportation applications.https://www.mdpi.com/2220-9964/14/4/172origin–destination matrixgenerative adversarial networksintelligent transportation systemsgravity modelradiation
spellingShingle Zehao Yuan
Xuanyan Chen
Biyu Chen
Yubo Luo
Yu Zhang
Wenxin Teng
Chao Zhang
Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
ISPRS International Journal of Geo-Information
origin–destination matrix
generative adversarial networks
intelligent transportation systems
gravity model
radiation
title Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
title_full Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
title_fullStr Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
title_full_unstemmed Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
title_short Generating Large-Scale Origin–Destination Matrix via Progressive Growing Generative Adversarial Networks Model
title_sort generating large scale origin destination matrix via progressive growing generative adversarial networks model
topic origin–destination matrix
generative adversarial networks
intelligent transportation systems
gravity model
radiation
url https://www.mdpi.com/2220-9964/14/4/172
work_keys_str_mv AT zehaoyuan generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT xuanyanchen generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT biyuchen generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT yuboluo generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT yuzhang generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT wenxinteng generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel
AT chaozhang generatinglargescaleorigindestinationmatrixviaprogressivegrowinggenerativeadversarialnetworksmodel