A Graph-Based System for PM2.5 Prediction

Kotcharat Kitchat; Isariya Sirivejabandhu; Yen Chang Liang; Min Te Sun; Kazuya Sakai; Wei Shinn Ku; Fang Yi Cheng; Scott Chih Hao Huang; Tsì Uí İk; Thattapon Surasak

doi:10.1007/978-981-96-6291-3_1

A Graph-Based System for PM_2.5 Prediction

Kotcharat Kitchat
, Isariya Sirivejabandhu
, Yen Chang Liang
, Min Te Sun
, Kazuya Sakai
, Wei Shinn Ku
, Fang Yi Cheng
, Scott Chih Hao Huang
, Tsì Uí İk
, Thattapon Surasak

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Air pollution poses a global challenge, carrying serious risks to both human health and the environment. Fine particulate matter (PM_2.5) is a key factor contributing to respiratory and cardiovascular diseases. Therefore, accurate PM_2.5 prediction is essential for analyzing pollution trends, safeguarding public health, guiding environmental planning, and shaping policy decisions. In this study, we conducted extensive experiments to enhance PM_2.5 prediction and developed a robust prediction system. Our system incorporates multiple components, including AirBox and EPA data preprocessing, data fusion, feature engineering, feature selection, and the proposed prediction model, DCRNN-GS. Designed for iterative multi-step forecasting, our model utilizes data from the previous 24 h to predict PM_2.5 levels for the next 24 h. Experimental results demonstrate that our system surpasses state-of-the-art methods in PM_2.5 prediction performance.

Original language	English
Title of host publication	Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings
Editors	Lin Hui, Ching-Hsien Hsu, Somchoke Ruengittinun
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	3-17
Number of pages	15
ISBN (Print)	9789819662906
DOIs	https://doi.org/10.1007/978-981-96-6291-3_1
State	Published - 2026
Event	13th International Conference on Ubi-Media Computing, Ubi-Media 2025 and 17th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2025 - Bangkok, Thailand Duration: 19 Jan 2025 → 23 Jan 2025

Publication series

Name	Communications in Computer and Information Science
Volume	2380 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	13th International Conference on Ubi-Media Computing, Ubi-Media 2025 and 17th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2025
Country/Territory	Thailand
City	Bangkok
Period	19/01/25 → 23/01/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Air Quality
Data Fusion
Deep Learning
Graph-based model
PM2.5 Prediction
Spatio-Temporal Feature

Access to Document

10.1007/978-981-96-6291-3_1

Cite this

Kitchat, K., Sirivejabandhu, I., Liang, Y. C., Sun, M. T., Sakai, K., Ku, W. S., Cheng, F. Y., Huang, S. C. H., İk, T. U., & Surasak, T. (2026). A Graph-Based System for PM_2.5 Prediction. In L. Hui, C.-H. Hsu, & S. Ruengittinun (Eds.), Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings (pp. 3-17). (Communications in Computer and Information Science; Vol. 2380 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-6291-3_1

Kitchat, Kotcharat ; Sirivejabandhu, Isariya ; Liang, Yen Chang et al. / A Graph-Based System for PM_2.5 Prediction. Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings. editor / Lin Hui ; Ching-Hsien Hsu ; Somchoke Ruengittinun. Springer Science and Business Media Deutschland GmbH, 2026. pp. 3-17 (Communications in Computer and Information Science).

@inproceedings{054788d5fc714eb3a14c1cb33c36c6f5,

title = "A Graph-Based System for PM2.5 Prediction",

abstract = "Air pollution poses a global challenge, carrying serious risks to both human health and the environment. Fine particulate matter (PM2.5) is a key factor contributing to respiratory and cardiovascular diseases. Therefore, accurate PM2.5 prediction is essential for analyzing pollution trends, safeguarding public health, guiding environmental planning, and shaping policy decisions. In this study, we conducted extensive experiments to enhance PM2.5 prediction and developed a robust prediction system. Our system incorporates multiple components, including AirBox and EPA data preprocessing, data fusion, feature engineering, feature selection, and the proposed prediction model, DCRNN-GS. Designed for iterative multi-step forecasting, our model utilizes data from the previous 24 h to predict PM2.5 levels for the next 24 h. Experimental results demonstrate that our system surpasses state-of-the-art methods in PM2.5 prediction performance.",

keywords = "Air Quality, Data Fusion, Deep Learning, Graph-based model, PM2.5 Prediction, Spatio-Temporal Feature",

author = "Kotcharat Kitchat and Isariya Sirivejabandhu and Liang, \{Yen Chang\} and Sun, \{Min Te\} and Kazuya Sakai and Ku, \{Wei Shinn\} and Cheng, \{Fang Yi\} and Huang, \{Scott Chih Hao\} and İk, \{Ts{\`i} U{\'i}\} and Thattapon Surasak",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 13th International Conference on Ubi-Media Computing, Ubi-Media 2025 and 17th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2025 ; Conference date: 19-01-2025 Through 23-01-2025",

year = "2026",

doi = "10.1007/978-981-96-6291-3\_1",

language = "???core.languages.en\_GB???",

isbn = "9789819662906",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "3--17",

editor = "Lin Hui and Ching-Hsien Hsu and Somchoke Ruengittinun",

booktitle = "Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings",

}

Kitchat, K, Sirivejabandhu, I, Liang, YC, Sun, MT, Sakai, K, Ku, WS, Cheng, FY, Huang, SCH, İk, TU & Surasak, T 2026, A Graph-Based System for PM_2.5 Prediction. in L Hui, C-H Hsu & S Ruengittinun (eds), Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings. Communications in Computer and Information Science, vol. 2380 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 3-17, 13th International Conference on Ubi-Media Computing, Ubi-Media 2025 and 17th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2025, Bangkok, Thailand, 19/01/25. https://doi.org/10.1007/978-981-96-6291-3_1

A Graph-Based System for PM_2.5 Prediction. / Kitchat, Kotcharat; Sirivejabandhu, Isariya; Liang, Yen Chang et al.
Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings. ed. / Lin Hui; Ching-Hsien Hsu; Somchoke Ruengittinun. Springer Science and Business Media Deutschland GmbH, 2026. p. 3-17 (Communications in Computer and Information Science; Vol. 2380 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Graph-Based System for PM2.5 Prediction

AU - Kitchat, Kotcharat

AU - Sirivejabandhu, Isariya

AU - Liang, Yen Chang

AU - Sun, Min Te

AU - Sakai, Kazuya

AU - Ku, Wei Shinn

AU - Cheng, Fang Yi

AU - Huang, Scott Chih Hao

AU - İk, Tsì Uí

AU - Surasak, Thattapon

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - Air pollution poses a global challenge, carrying serious risks to both human health and the environment. Fine particulate matter (PM2.5) is a key factor contributing to respiratory and cardiovascular diseases. Therefore, accurate PM2.5 prediction is essential for analyzing pollution trends, safeguarding public health, guiding environmental planning, and shaping policy decisions. In this study, we conducted extensive experiments to enhance PM2.5 prediction and developed a robust prediction system. Our system incorporates multiple components, including AirBox and EPA data preprocessing, data fusion, feature engineering, feature selection, and the proposed prediction model, DCRNN-GS. Designed for iterative multi-step forecasting, our model utilizes data from the previous 24 h to predict PM2.5 levels for the next 24 h. Experimental results demonstrate that our system surpasses state-of-the-art methods in PM2.5 prediction performance.

AB - Air pollution poses a global challenge, carrying serious risks to both human health and the environment. Fine particulate matter (PM2.5) is a key factor contributing to respiratory and cardiovascular diseases. Therefore, accurate PM2.5 prediction is essential for analyzing pollution trends, safeguarding public health, guiding environmental planning, and shaping policy decisions. In this study, we conducted extensive experiments to enhance PM2.5 prediction and developed a robust prediction system. Our system incorporates multiple components, including AirBox and EPA data preprocessing, data fusion, feature engineering, feature selection, and the proposed prediction model, DCRNN-GS. Designed for iterative multi-step forecasting, our model utilizes data from the previous 24 h to predict PM2.5 levels for the next 24 h. Experimental results demonstrate that our system surpasses state-of-the-art methods in PM2.5 prediction performance.

KW - Air Quality

KW - Data Fusion

KW - Deep Learning

KW - Graph-based model

KW - PM2.5 Prediction

KW - Spatio-Temporal Feature

UR - https://www.scopus.com/pages/publications/105011952799

U2 - 10.1007/978-981-96-6291-3_1

DO - 10.1007/978-981-96-6291-3_1

M3 - 會議論文篇章

AN - SCOPUS:105011952799

SN - 9789819662906

T3 - Communications in Computer and Information Science

SP - 3

EP - 17

BT - Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings

A2 - Hui, Lin

A2 - Hsu, Ching-Hsien

A2 - Ruengittinun, Somchoke

PB - Springer Science and Business Media Deutschland GmbH

T2 - 13th International Conference on Ubi-Media Computing, Ubi-Media 2025 and 17th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2025

Y2 - 19 January 2025 through 23 January 2025

ER -

Kitchat K, Sirivejabandhu I, Liang YC, Sun MT, Sakai K, Ku WS et al. A Graph-Based System for PM_2.5 Prediction. In Hui L, Hsu CH, Ruengittinun S, editors, Ubi-Media Computing, Pervasive Systems, Algorithms and Networks - 13th International Conference, Ubi-Media 2025, and 17th International Symposium, I-SPAN 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 3-17. (Communications in Computer and Information Science). doi: 10.1007/978-981-96-6291-3_1

A Graph-Based System for PM2.5 Prediction