Multi‑step solar ultraviolet index prediction: integrating convolutional neural networks with long short‑term memory for a representative case study in Queensland, Australia
Article
| Article Title | Multi‑step solar ultraviolet index prediction: integrating convolutional |
|---|---|
| ERA Journal ID | 213704 |
| Article Category | Article |
| Authors | AL-Musaylh, Mohan, Al‑Dafaie, Kadhem, Downs, Nathan, Ghimire, Sujan, Ali, Mumtaz, Yaseen, Zaher Mundher, Igoe, Damien P., Deo, Ravinesh C., Paris, Alfo V. and A. Jebar, Mustapha A. |
| Journal Title | Modeling Earth Systems and Environment |
| Journal Citation | 11 |
| Article Number | 77 |
| Number of Pages | 17 |
| Year | 2025 |
| Publisher | Springer |
| Place of Publication | Germany |
| ISSN | 2363-6203 |
| 2363-6211 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/s40808-024-02282-y |
| Web Address (URL) | https://link.springer.com/article/10.1007/s40808-024-02282-y |
| Abstract | The impact of solar ultraviolet (UV) radiation on public health is severe and can cause sunburn, skin aging and cancer, immunosuppression, and eye damage. Minimization of exposure to solar UV is required in order to reduce the risks of these illnesses to the public. Greater public awareness and the prediction of ultraviolet index (UVI) is considered an essential task for the minimization of solar UV exposures. This research has designed an artificial intelligence (AI) model to predict the multistep solar UVI. The proposed model was based on the integration of convolutional neural networks with long short-term memory network (CLSTM) as the primary model to predict solar UVI, tested for Brisbane (27.47°S, 153.02°E), the capital city in Queensland, Australia. Solar zenith angle (SZA) data were used together with UVI as inputs for the CLSTM of different scales (i.e., 10-min, 30-min, and 60-min) UVI prediction. The CLSTM model was benchmarked against well-established AI models e.g., long short-term memory network (LSTM), convolutional neural network (CNN), Deep Neural Network (DNN), multilayer perceptron (MLP), extreme learning machine (ELM), random forest regression (RFR), Extreme Gradient Boosting (XGB), and Pro6UV Deterministic models. The experimental results showed that the CLSTM model outperformed these models with Root Mean Square Error (RMSE = 0.3817), Mean Absolute Error (MAE = 0.1887), and Relative Root Mean Square Error (RRMSE = 8.0086%), for 10-min prediction. Whereas, for 30-min and 60-min prediction were RMSE = 0.4866/0.5146, MAE = 0.2763/0.3038, RRMSE = 10.4860%/11.5840%, respectively. The research finding confirmed the potential of the proposed data-intelligent model (i.e., CLSTM) can yield improved UVI prediction for both the public and the government agencies. |
| Keywords | Artifcial intelligence ; Decision making; Intelligent risk alarm ; Deep learning; Solar predicted models; Ultraviolet radiation |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | Southern Technical University, Iraq |
| Al-Muthanna University, Iraq | |
| University of Southern Queensland | |
| King Fahd University of Petroleum and Minerals, Saudi Arabia | |
| University of Thi-Qar, Iraq | |
| Al-Ayen University, Iraq |
https://research.usq.edu.au/item/zv26q/multi-step-solar-ultraviolet-index-prediction-integrating-convolutional-neural-networks-with-long-short-term-memory-for-a-representative-case-study-in-queensland-australia
199
total views1
total downloads32
views this month0
downloads this month