Air quality prediction enhanced by a CNN-LSTM-Attention model optimized with an advanced dung beetle algorithm

Authors

  • Xiaojie Zhou
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia; Weifang University of Science and Technology, Shouguang 262713, China
  • Majid Khan Majahar Ali
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia
  • Farah Aini Abdullah
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia
  • Lili Wu
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia
  • Ying Tian
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia
  • Tao Li
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia
  • Kaihui Li
    School of Mathematical Sciences, Universiti Sains Malaysia, Pulau Pinang 11800, Malaysia

Keywords:

Air quality prediction, DBO, CNN, LSTM, Attention

Abstract

Air pollution significantly impacts human health and socioeconomic development, making accurate air quality prediction crucial. This study proposes a hybrid CNN-LSTM-Attention model optimized with an improved Dung Beetle Optimization (IDBO) algorithm to enhance predictive performance. IDBO integrates multiple strategies to improve global search capabilities and overcome the limitations of conventional DBO. Experiments using PM2.5 data from Penang, Malaysia, demonstrate that the proposed model outperforms other models across multiple evaluation metrics R2 = 0.904, RMSE = 2.677, MSE = 7.168, MAE = 1.982, MAPE = 44.1% The findings validate the effectiveness of the proposed approach in improving air quality prediction, offering valuable insights for environmental monitoring and pollution control.

Dimensions

[1] A. Binbusayyis, M. A. Khan, A. M. M. Ahmed & W. R. S. Emmanuel“A deep learning approach for prediction of air quality index in smart city”, Discover Sustainability 5 (2024) 272. https://doi.org/10.1007/s43621-024-00272-9.

[2] E. X. Neo, K. Hasikin, K. W. Lai, M. I. Mokhtar, M. M. Azizan, H. F. Hizaddin, S. A. Razak & Yanto, “Artificial intelligence-assisted air quality monitoring for smart city management”, PeerJ Computer Science 9 (2023) e1306. https://doi.org/10.7717/peerj-cs.1306.

[3] A. Tella & A.-L. Balogun, “GIS-based air quality modelling: Spatial prediction of PM10 for Selangor State, Malaysia using machine learning algorithms”, Environmental Science and Pollution Research 29 (2022) 86109. https://doi.org/10.1007/s11356-021-16150-0.

[4] N. H. Van, P. Van Thanh, D. N. Tran & D.-T. Tran, “A new model of air quality prediction using lightweight machine learning”, International Journal of Environmental Science and Technology 20 (2023) 2983. https://doi.org/10.1007/s13762-022-04185-w.

[5] H. Xu, Y. Chong, Y. Liu, W. Cao, D. Xu, J. Zhang & J. Zhao, “Prediction study of ARIMA-BPNN model in tuberculosis incidence rate”, Journal of Medical Pest Control 10 (n.d.) 970. https://www.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&dbname=CJFDLAST2024&filename=YXDZ202410008&uniplatform=OVERSEA&v=xU3b51NBam19ZNudj4ZIa0sjORnAfzn54FvZvv0msOeQ-6iZdfOFOfNiOhWhg1.

[6] H. Zhou, T. Wang, H. Zhao & Z. Wang, “Updated prediction of air quality based on Kalman-attention-LSTM network”, Sustainability 15 (2023) 1. https://doi.org/10.3390/su15010356.

[7] R. Zhou, X. Ma, H. Dong, J. Zeng, L. Yao & Z. Zhao, “Comparison of the effectiveness of ARIMA model and GM (1,1) in predicting the epidemic trend of other infectious diarrheal diseases”, Journal of Medical Pest Control 10 (n.d.) 955–960. https://www.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&dbname=CJFDLAST2024&filename=YXDZ202410005&uniplatform=OVERSEA&v=xU3b51NBa_n3s_tDp6hLQnahstDiuyjjtGb7Qi0902PSiJw6uBk2LkcbQ0UZbvgF

[8] K. Wang & H. Li, “Air pollution index prediction model based on multiple linear regression”, Information Recording Materials 25 (2024) 1. https://doi.org/10.16009/j.cnki.cn13-1295/tq.2024.02.008.

[9] C. Ren & G. Xie, “Prediction of PM2.5 concentration level based on random forest and meteorological parameters”, Computer Engineering and Applications 2 (2024) 213. https://www.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&dbname=CJFDLAST2019&filename=JSGG201902034&uniplatform=OVERSEA&v=M9qWRE8bApgTBqHdcQIIN8H-kZWrVv6hKI4Oz4b9FiylcX34qSwe2fWgfFidmU.

[10] Y. Song, Y. Xu & Y. Zhang, “Seasonal PM2.5 prediction based on SARIMA-SVM model”, Computer Engineering 01 (2024) 51. https://doi.org/10.19678/j.issn.1000-3428.0068372.

[11] S. Sheng & W. Yuan, “Short-term wind speed prediction based on quadratic decomposition and BiLSTM-XGBoost-ARIMA combination model”, Journal of North China Electric Power University 2024 (2024) 1. https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=HBDL20240725003.

[12] J. Duan, Y. Gong, J. Luo & Z. Zhao, “Air-quality prediction based on the ARIMA-CNN-LSTM combination model optimized by dung beetle optimizer”, Scientific Reports 13 (2023) 12127. https://doi.org/10.1038/s41598-023-36620-4.

[13] Q. Wu & H. Lin, “Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network”, Sustainable Cities and Society 50 (2019) 101657. https://doi.org/10.1016/j.scs.2019.101657.

[14] A. T. Nguyen, D. H. Pham, B. L. Oo, Y. Ahn & B. T. H. Lim, “Predicting air quality index using attention hybrid deep learning and quantuminspired particle swarm optimization”, Journal of Big Data 11 (2024) 926. https://doi.org/10.1186/s40537-024-00926-5.

[15] X. Liu & H. Guo, “Air quality indicators and AQI prediction coupling long-short term memory (LSTM) and sparrow search algorithm (SSA): A case study of Shanghai”, Atmospheric Pollution Research 13 (2022) 101551. https://doi.org/10.1016/j.apr.2022.101551.

[16] Q. Shao, J. Chen & T. Jiang, “A novel coupled optimization prediction model for air quality”, IEEE Access 11 (2023) 69667. https://doi.org/10.1109/ACCESS.2023.3293249.

[17] K. Wu, Y. Chai, X. Zhang & X. Zhao, “Research on power price forecasting based on PSO-XGBoost”, Electronics 11 (2022) 22. https://doi.org/10.3390/electronics11223763.

[18] J. Zhu, S. Zhang, T. Zhang, J. Sun & Z. Zhang, “Air quality prediction based on two-layer decomposition and improved sand cat swarm optimization”, Foreign Electronic Measurement Technology 5 (2024) 190. https://doi.org/10.19652/j.cnki.femt.2305800.

[19] X. Wang, Y. Wei, Z. Guo, J. Wang, H. Yu & B. Hu, “A Sinh-Coshenhanced DBO algorithm applied to global optimization problems”, Biomimetics 9 (2024) 271. https://doi.org/10.3390/biomimetics9050271.

[20] Tanyildizi, E., & Demir, G. (2017). Golden sine algorithm: a novel mathinspired algorithm. Advances in Electrical & Computer Engineering, 17 (2017) 71. http://dx.doi.org/10.4316/AECE.2017.02010.

[21] J. Liu, L. Cong, Y. Xia, G. Pan, H. Zhao & Z. Han, “Short-term power load prediction based on DBO-VMD and an IWOA-BILSTM neural network combination model”, Dianli Xitong Baohu Yu Kongzhi/Power System Protection and Control 52 (2024) 123. https://doi.org/10.19783/j.cnki.pspc.231402.

[22] R. Rajabioun, “Cuckoo optimization algorithm”, Applied Soft Computing 11 (2011) 5508. https://doi.org/10.1016/j.asoc.2011.05.008.

Published

2025-08-01

How to Cite

Air quality prediction enhanced by a CNN-LSTM-Attention model optimized with an advanced dung beetle algorithm. (2025). Journal of the Nigerian Society of Physical Sciences, 7(3), 2473. https://doi.org/10.46481/jnsps.2025.2473

Issue

Volume 7, Issue 3, August 2025

Section

Computer Science
Copyright & Licensing

Copyright (c) 2025 xiaojie zhou, Majid Khan Majahar Ali, Farah Aini Abdullah, Lili Wu, Ying Tian, Tao Li, Kaihui Li

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Air quality prediction enhanced by a CNN-LSTM-Attention model optimized with an advanced dung beetle algorithm. (2025). Journal of the Nigerian Society of Physical Sciences, 7(3), 2473. https://doi.org/10.46481/jnsps.2025.2473

Most read articles by the same author(s)