Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


![Figure 3 Post-training optimisation methods provided by TensorFlow [46].](https://figures.cochat.ai/paper-figures/072c025c2c854ac7aa37eead2073d8f1/optimising-deep-learning-at-the-edge-for-accurate-hourly-air-quality-prediction-figure-3.jpg)













Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Pruning techniques allow removal of redundant structures of network and parameters [15,16].”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [16]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“For instance, using quantization techniques, which are conversion techniques that convert float-point numbers to minimize precision numbers, intending to shrink the size of the DL model with minimal degradation of accuracy.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [16]
The cited source says what the claim attributes to it.
In the citing paper
“Furthermore, deployment of pre-trained DL models into tiny edge devices is now possible, after performing some techniques to compress DL models and optimize the inference.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [16]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“Long Short-Term Memory (LSTM) [45] is a structural modification of the Recurrent Neural Network (RNN) that adds memory cells in the hidden layer so that it can be implemented to control the flow of information in time-series data.”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2014) · Cited by 33,419
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · cited 1×
“Moreover, edge computing can address energy-aware and bandwidth saving applications [5].”
BackgroundFine Particulate Air Pollution and Hospital Admission for Cardiovascular and Respiratory Diseases
Dominici, F., Peng, R. D., Bell, M. L., Pham, L., McDermott, A., Zeger, S. L., & Samet, J. M. (2006) · JAMA · doi:10.1001/jama.295.10.1127 · Cited by 2,634 · cited 1×
“It may lead to lung cancer [20], affect cardiovascular diseases [21] and even result in death [22].”
BackgroundDeep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540 · cited 5×
“Both ASICs and FPGAs are generally more energy-efficient than conventional CPUs and GPUs [4].”
BackgroundMethodInfluentialA Survey on the Edge Computing for the Internet of Things
Yu, W., Liang, F., He, X., Hatcher, W. G., Lu, C., Lin, J., & Yang, X. (2018) · IEEE Access · doi:10.1109/access.2017.2778504 · Cited by 1,520 · cited 1×
“Edge computing refers to the deployment of computation closer to data sources (edge) [1], rather than more centrally as is the case with cloud computing.”
BackgroundConvergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498 · cited 1×
“For data processing and information inference, it is also possible to embed intelligence at edge devices, which can be enabled by machine learning (ML) algorithms [6,7].”
BackgroundOutdoor Particulate Matter Exposure and Lung Cancer: A Systematic Review and Meta-Analysis
Hamra, G. B., Guha, N., Cohen, A., Laden, F., Raaschou-Nielsen, O., Samet, J. M., Vineis, P., Forastiere, F., Saldiva, P., Yorifuji, T., et al. (2014) · Environmental Health Perspectives · doi:10.1289/ehp/1408092 · Cited by 1,023
Evaluating Critical Security Issues of the IoT World: Present and Future Challenges
Frustaci, M., Pace, P., Aloi, G., & Fortino, G. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2017.2767291 · Cited by 764 · cited 1×
“It can address latency, privacy and scalability issues faced by cloud-based systems [2,3].”
Background
Research works printed but not linked: 7
- Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv.
- Xu, J., Chen, L., Lv, M., Zhan, C., Chen, S., and Chang, J. (2021). HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method. arXiv.
- Zhang, Q., Lam, J.C., Li, V.O., and Han, Y. (2020). Deep-AIR: A Hybrid CNN-LSTM Framework forFine-Grained Air Pollution Forecast. arXiv.
- Chen, H.C., Putra, K.T., and Chun-WeiLin, J. (2021). A Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks. arXiv.
- Wu, H., Judd, P., Zhang, X., Isaev, M., and Micikevicius, P. (2020). Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation. arXiv.
- Li, J., and Alvarez, R. (2021). On the quantization of recurrent neural networks. arXiv.
- Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv.
Cited by
Air-pollution prediction in smart city, deep learning approach
Bekkar, A., Hssina, B., Douzi, S., & Douzi, K. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00548-1 · Cited by 296
“Four recently published models are suggested, such as AC-LSTM by [53], LSTM-FC by [33], XGBoost by [54], and CNN-LSTM by [55], which are evaluated for comparing the performance of the proposed model.”
MethodBourechak, A., Zedadra, O., Kouahla, M. N., Guerrieri, A., Seridi, H., & Fortino, G. (2023) · Sensors · doi:10.3390/s23031639 · Cited by 258
“[24] On-device airquality prediction Prediction CNN, LSTM Dataset from University of California–Irvine (UCI) Machine Learning Repository page Edge devices(RPi3B+, RPi4B) Posttraining quantization Hardware accelerator TensorFlow Lite RMSE, MAE execution time Low-complexity model latency Accuracy degradation”
MethodAlajlan, N. N., & Ibrahim, D. M. (2022) · Micromachines · doi:10.3390/mi13060851 · Cited by 224
“Pruning techniques allow removal of redundant structures of network and parameters [15,16].”
MethodJouini, O., Sethom, K., Namoun, A., Aljohani, N. F., Alanazi, M. H., & Alanazi, M. N. (2024) · Technologies · doi:10.3390/technologies12060081 · Cited by 202
“…consisting of various devices such as NVIDIA Jetson Nx and Jetson Nano to collect water sensor data and to perform real-time video-based fish detection using DL. Wardana et al. [77] introduced a new DL model that integrates one-dimensional CNN and LSTM network to anticipate a short-term hourly PM2.”
Deep-learning architecture for PM2.5 concentration prediction: A review
Zhou, S., Wang, W., Zhu, L., Qiao, Q., & Kang, Y. (2024) · Environmental Science and Ecotechnology · doi:10.1016/j.ese.2024.100400 · Cited by 135
Metadata
- Authors
- Wardana, I. N. K., Gardner, J. W., & Fahmy, S. A.
- Affiliations
- University of Warwick (GB)
- Corresponding author
- Wardana, I Nyoman Kusuma
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-02-04
- Volume
- 21
- Issue
- 4
- Pages
- 1064
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7913936
- OpenAlex
- W3126841703
- Cited by
- 61
- References
- 41
- Citations by year
- 2026: 10 · 2025: 8 · 2024: 14 · 2023: 16 · 2022: 11 · 2021: 2
- FWCI
- 3.48
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Warwick Research Archive Portal (University of Warwick) (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) (submittedVersion, other-oa)
- Funders
- Lembaga Pengelola Dana Pendidikan (Ref: S-1027/LPDP.4/2019)
- Topics
- Physical Sciences › Environmental Science › Environmental Engineering › Air Quality Monitoring and Forecasting
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- air quality forecasting, PM2.5, edge computing, CNN-LSTM hybrid model, model compression, Raspberry Pi, inference latency, sensor networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction. https://app.cochat.ai/papers/10.3390/s21041064
- The paper
- Wardana, I. N. K., Gardner, J. W., & Fahmy, S. A. (2021). Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction. Sensors. https://doi.org/10.3390/s21041064
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.