Deep Learning for PM2.5 Forecasting: An Empirical Comparison of LSTM, GRU, and N-BEATS
References
- Calzada I. Democratising Smart Cities? Penta-Helix Multistakeholder Social Innovation Framework. Smart Cities 2020:3(4):1145–1172. https://doi.org/10.3390/smartcities3040057
- Zou Z., Cheng C., Shen S. The Complex Nonlinear Coupling Causal Patterns Between PM2.5 and Meteorological Factors in Tibetan Plateau: A Case Study in Xining. IEEE Access 2021:9:150373–150382. https://doi.org/10.1109/ACCESS.2021.3123455
- Li T., Hua M., Wu X. A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5). IEEE Access 2020:8:26933–26940. https://doi.org/10.1109/ACCESS.2020.2971348
- Qin D., Yu J., Zou G., Yong R., Zhao Q., Zhang B. A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration. IEEE Access 2019:7:20050–20059. https://doi.org/10.1109/ACCESS.2019.2897028
- Yang J., Ismail A. W., Li Y., Zhang L., Fadzli F. E. Transfer Learning-Driven Hourly PM2.5 Prediction Based on a Modified Hybrid Deep Learning. IEEE Access 2023:11:99614–99627. https://doi.org/10.1109/ACCESS.2023.3314490
- Putri T. H., Caraka R. E., Toharudin T., Kim Y., Chen R.-C., Gio P. U., Sakti A. D., Pontoh R. S., Pratiwi I. R., Nugraha F. A. L., Azzahra T. S., Cerelia J. J., Darmawan G., Faidah D. Y., Pardamean B. Fine-Tuning of Predictive Models CNN-LSTM and CONV-LSTM for Nowcasting PM2.5 Level. IEEE Access 2024:12:28988–29003. https://doi.org/10.1109/ACCESS.2024.3368034
- Wang L., Jin X., Huang Z., Zhu H., Chen Z., Liu Y., Feng H. Short-Term PM2.5 Prediction Based on Multi-Modal Meteorological Data for Consumer-Grade Meteorological Electronic Systems. IEEE Transactions on Consumer Electronics 2024:70(1):3464–3474. https://doi.org/10.1109/TCE.2024.3354073
- Qiao W., Tian W., Tian Y., Yang Q., Wang Y., Zhang J. The Forecasting of PM2.5 Using a Hybrid Model Based on Wavelet Transform and an Improved Deep Learning Algorithm. IEEE Access 2019:7:142814–142825. https://doi.org/10.1109/ACCESS.2019.2944755
- Kristiani E., Kuo T.-Y., Yang C.-T., Pai K.-C., Huang C.-Y., Nguyen K. L. P. PM2.5 Forecasting Model Using a Combination of Deep Learning and Statistical Feature Selection. IEEE Access 2021:9:68573–68582. https://doi.org/10.1109/ACCESS.2021.3077574
- Nguyen M. H., Le Nguyen P., Nguyen K., Le V. A., Nguyen T.-H., Ji Y. PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model. IEEE Access 2021:9:57338–57350. https://doi.org/10.1109/ACCESS.2021.3072280
- Yang M.-C., Chen M. C. Composite Neural Network: Theory and Application to PM2.5 Prediction. IEEE Transactions on Knowledge and Data Engineering 2023:35(2):1311–1323. https://doi.org/10.1109/TKDE.2021.3099135
- Sirisumpun N., Wongwailikhit K., Painmanakul P., Vateekul P. Spatio-Temporal PM2.5 Forecasting in Thailand Using Encoder-Decoder Networks. IEEE Access 2023:11:69601–69613. https://doi.org/10.1109/ACCESS.2023.3293398
- Ma J., Ding Y., Gan V. J. L., Lin C., Wan Z. Spatiotemporal Prediction of PM2.5 Concentrations at Different Time Granularities Using IDW-BLSTM. IEEE Access 2019:7:107897–107907. https://doi.org/10.1109/ACCESS.2019.2932445
- Chiang Y.-L., Wang J.-C., Lee M.-H., Liu A.-C., Jiang J.-A. Deep-Learning-Based Multi-Timestamp Multi-Location PM2.5 Prediction: Verification by Using a Mobile Monitoring System With an IoT Framework Deployed in the Urban Zone of a Metropolitan Area. IEEE Internet of Things Journal 2024:11(5):8815–8837. https://doi.org/10.1109/JIOT.2023.3322862
- Chang S.-W., Chang C.-L., Li L.-T., Liao S.-W. Reinforcement Learning for Improving the Accuracy of PM2.5 Pollution Forecast Under the Neural Network Framework. IEEE Access 2020:8:9864–9874. https://doi.org/10.1109/ACCESS.2019.2932413
- Wang H., Chen H. A Novel Particulate Matter 2.5 Concentration Prediction Model Based on Double-Layer Decomposition and Feedback of Model Learning Effect. IEEE Access 2022:10:12164–12178. https://doi.org/10.1109/ACCESS.2022.3146170
- Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation 1997:9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
- Wang C., Han D., Liu Q., Luo S. A Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM. IEEE Access 2019:7:2161–2168. https://doi.org/10.1109/ACCESS.2018.2887138
- Li X., Xu X., Wang J., Li J., Qin S., Yuan J. Study on Prediction Model of HIV Incidence Based on GRU Neural Network Optimized by MHPSO. IEEE Access 2020:8:49574–49583. https://doi.org/10.1109/ACCESS.2020.2979859
- Jin Y.-C., Cao Q., Sun Q., Lin Y., Liu D.-M., Shan-Yu, Wang C.-X., Wang X.-L., Wang X.-Y. Models for COVID-19 Data Prediction Based on Improved LSTM-ARIMA Algorithms. IEEE Access 2024:12:3981–3991. https://doi.org/10.1109/ACCESS.2023.3347403
- Ma L., Tian S. A Hybrid CNN-LSTM Model for Aircraft 4D Trajectory Prediction. IEEE Access 2020:8:134668–134680. https://doi.org/10.1109/ACCESS.2020.3010963
- Cho K., van Merriënboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., Bengio Y. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2014:1724–1734. https://doi.org/10.3115/v1/D14-1179
- Liu F., Zhang Z., Zhou R. Automatic modulation recognition based on CNN and GRU. Tsinghua Science and Technology 2022:27(2):422–431. https://doi.org/10.26599/TST.2020.9010057
- Cong Y., Zhao X., Tang K., Wang G., Hu Y., Jiao Y. FA-LSTM: A Novel Toxic Gas Concentration Prediction Model in Pollutant Environment. IEEE Access 2022:10:1591–1602. https://doi.org/10.1109/ACCESS.2021.3133497
- Sheng A., Xie L., Zhou Y., Wang Z., Liu Y. A Hybrid Model Based on Complete Ensemble Empirical Mode Decomposition With Adaptive Noise, GRU Network and Whale Optimization Algorithm for Wind Power Prediction. IEEE Access 2023:11:62840–62854. https://doi.org/10.1109/ACCESS.2023.3287319
- Zhang Y., Suzuki G., Shioya H. Prediction and Detection of Sewage Treatment Process Using N-BEATS Autoencoder Network. IEEE Access 2022:10:112594–112608. https://doi.org/10.1109/ACCESS.2022.3216924
- Motavali A., Yow K.-C., Hansmeier N., Chao T.-C. DSA-BEATS: Dual Self-Attention N-BEATS Model for Forecasting COVID-19 Hospitalization. IEEE Access 2023:11:137352–137365. https://doi.org/10.1109/ACCESS.2023.3318931
- Oreshkin B.N., Carpov D., Chapados N., Bengio Y. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. Proceedings of the International Conference on Learning Representations (ICLR) 2020. https://doi.org/10.48550/arXiv.1905.10437
- Ji W., Zhu D. ECG Classification Exercise Health Analysis Algorithm Based on GRU and Convolutional Neural Network. IEEE Access 2024:12:59842–59850. https://doi.org/10.1109/ACCESS.2024.3392965
- Olivares K.G., Challu C., Marcjasz G., Weron R., Dubrawski A. Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx. International Journal of Forecasting 2023:39(2):884-900. https://doi.org/10.1016/j.ijforecast.2022.03.001
- Chen S. Beijing PM2.5 [Dataset]. UCI Machine Learning Repository, 2015. https://doi.org/10.24432/C5JS49
- Sprudza K. L., Klavina A., Berzina B., Kauce R., Martinsone Z. Indoor Air Quality Guidelines Connection to IAQ Certification and Labelling Process. Environmental and Climate Technologies 2023:27(1):28–39. https://doi.org/10.2478/rtuect-2023-0003
- Ali H., Dedov A., Volkova A. Exploring Heat Demand Forecasting in District Heating Networks Using Random Parameter Linear Regression Model. Environmental and Climate Technologies 2024:28(1):670–685. https://doi.org/10.2478/rtuect-2024-0052
- Ali D. M. T. E., Motuzienė V. Data Challenges in AI-Driven HVAC Systems: A Critical Analysis and Future Directions. Environmental and Climate Technologies 2025:29(1):527–539. https://doi.org/10.2478/rtuect-2025-0036
- Chiteka K., Enweremadu C. An Empirical Approach to Solar Photovoltaic Cell Temperature Prediction. Environmental and Climate Technologies 2024:28(1):422–436. https://doi.org/10.2478/rtuect-2024-0033
- Beltrán-Velamazán C., Gómez-Gil M., Monzón-Chavarrías M., Espinosa-Fernández A., López-Mesa B. Harnessing Open European Data for a Data-Driven Approach to Enhancing Decarbonization Measurement in the Built Environment. Environmental and Climate Technologies 2024:28(1):776–793. https://doi.org/10.2478/rtuect-2024-0060
DOI: https://doi.org/10.2478/rtuect-2026-0036 | Journal eISSN: 2255-8837 (formerly 2255-8845) | Journal ISSN: 1691-5208
Language: English
Page range: 526 - 541
Submitted on: Mar 16, 2026
Accepted on: Apr 20, 2026
Published online: Oct 23, 2026
Published in print: Jan 1, 2026
Published by: Riga Technical University
In partnership with: Paradigm Publishing Services
Publication frequency: Volume open
Keywords:
Related subjects:
© 2026 Murad A. Yaghi, Huthaifa Al-Omari, Salem Alemaishat, Raghad Abu Wadi, published by Riga Technical University
This work is licensed under the Creative Commons Attribution 4.0 License.