Improving One-Day-Ahead Forecasting of Low-Latitude Amplitude Scintillation Using an Upsampling-Enhanced LSTM
| dc.contributor.author | Muangkammuen, Patinya | |
| dc.contributor.author | Suthisopapan, Puripong | |
| dc.contributor.author | Tongkasem, Napat | |
| dc.contributor.author | Supnithi, Pornchai | |
| dc.contributor.author | Kruesubthaworn, Anan | |
| dc.contributor.author | Klenzing, Jeff | |
| dc.contributor.author | Siritaratiwat, Apirat | |
| dc.date.accessioned | 2026-08-06T10:54:05Z | |
| dc.date.available | 2026-08-06T10:54:05Z | |
| dc.date.issued | 2026-01-01 | |
| dc.description.abstract | The scintillation in radio wave propagation, particularly in regions near the magnetic equator, is found to be introduced by the ionospheric irregularities causing unsatisfactory performance in satellite-based applications. In order to mitigate this effect, we design a long short-term memory (LSTM) model to forecast amplitude scintillation at 1-min resolution. In addition, the upsampling-based feature preprocessing is introduced to improve forecasting performance, especially for short-term severe scintillation events. In terms of R$^{2}$, which is a popular forecast evaluation metric, our proposed model exhibits about 20% improvement over the same LSTM model without upsampling. Furthermore, although existing studies achieve good forecasting accuracy up to 4 h ahead, the proposed model sets a benchmark with one-day-ahead forecasting, but at the cost of longer training time due to upsampling. | |
| dc.identifier.citation | IEEE Transactions on Aerospace and Electronic Systems, 62, 6087-6107, 2026 | |
| dc.identifier.doi | 10.1109/TAES.2026.3662676 | |
| dc.identifier.issn | 00189251 | |
| dc.identifier.other | 2-s2.0-105029952533 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/17726 | |
| dc.source | IEEE Transactions on Aerospace and Electronic Systems | |
| dc.subject | Feature preprocessing | |
| dc.subject | ionospheric scintillation | |
| dc.subject | long short-term memory (LSTM) network | |
| dc.subject | machine learning | |
| dc.subject | predictive models | |
| dc.subject | time-series forecasting | |
| dc.title | Improving One-Day-Ahead Forecasting of Low-Latitude Amplitude Scintillation Using an Upsampling-Enhanced LSTM | |
| dc.type | Article |
