|
Modeling Erythemal Ultraviolet Radiation in Thailand using Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost) |
|---|---|
| รหัสดีโอไอ | |
| Creator | Sumaman Buntoung |
| Title | Modeling Erythemal Ultraviolet Radiation in Thailand using Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost) |
| Contributor | Chaninat Srimueang, Somjet Pattarapanitchai, Jarungsang Laksanaboonsong, Serm Janjai |
| Publisher | Faculty of Science, Khon Kaen University |
| Publication Year | 2568 |
| Journal Title | KKU Science Journal |
| Journal Vol. | 53 |
| Journal No. | 3 |
| Page no. | 438-449 |
| Keyword | Erythemal Ultraviolet Radiation, Machine Learning, XGBoost, ANN |
| URL Website | https://ph01.tci-thaijo.org/index.php/KKUSciJ |
| Website title | Thai Journal Online (ThaiJO) |
| ISSN | 3027-6667 |
| Abstract | This study proposes machine learning models to estimate erythemal ultraviolet (EUV) radiation under all sky conditions using several available atmospheric and meteorological parameters. Data at four ground-based stations in key regions of Thailand namely, Chiang Mai, Ubon Ratchathani, Songkhla, and Nakhon Pathom, were collected from 2019 to 2023. Two well-known machine learning techniques, Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost), were developed and employed, and their performance was compared. The results show that XGBoost outperformed ANN in terms of accuracy, with the best performance at each site yielding normalized root mean square errors (nRMSE) ranging from 8.56% to 14.32%. This superior performance suggests that XGBoost is more effective for estimating EUV radiation in Thailand and could be further improved for radiation forecasting. |
