KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Supnithi, PornchaiSubject: search.filters.subject.Equatorial ionosphere

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep learning-based prediction models for the vertical total electron content using GNSS satellite observations
    (2026-08-01)
    Mutasov, Gleb
    ;
    Myint, Lin Min Min
    ;
    Budtho, Jirapoom
    ;
    Perwitasari, Septi
    ;
    Nishioka, Michi
    Ionospheric Total Electron Content (TEC) is a crucial parameter for characterizing the state of the ionosphere and assessing its impact on satellite-based navigation systems and on communication technologies. In equatorial and low-latitude regions, ionospheric irregularities, particularly equatorial plasma bubbles (EPBs), pose significant challenges for satellite navigation and communication due to their capacity to cause rapid TEC fluctuations and signal degradation. Since these effects are especially pronounced during ionospheric and geomagnetic disturbances, making accurate TEC prediction is an essential task for improving the reliability of GNSS-based positioning and space weather applications. This study presents a machine learning-based framework for one-day-ahead prediction of TEC with a 30-min resolution over the magnetic equator and low-latitude regions, with a focus on Southeast Asia. Unlike global models, our approach is tailored to local GNSS observations and directly predicts TEC values along specific satellite-receiver paths, defined by geographic location and satellite visibility. We integrate ionospheric pierce point (IPP) coordinates, geomagnetic indices, and solar activity indicators as features to enhance temporal and spatial forecasting accuracy. To address the nonlinear and nonstationary nature of TEC variations, we investigate and compare three deep learning architectures: a Transformer-based time-series model, a Temporal Kolmogorov–Arnold Network (TKAN), and a Long Short-Term Memory (LSTM). Additionally, the predictions are benchmarked against the empirical IRI-2020 model and a persistence baseline. The results demonstrate that both the Transformer and TKAN models outperform the LSTM and empirical approaches, particularly during different geomagnetic and ionospheric conditions, showing improved robustness and generalization. The proposed framework highlights the potential for accurate, resource-efficient TEC prediction in low-latitude regions and opens a pathway for further improvements by integrating multi-GNSS observations and additional space weather parameters.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The variation of equatorial spread-F occurrences observed by ionosondes at Thailand longitude sector
    (2013-11-15)
    Rungraengwajiake, Sarawoot
    ;
    Supnithi, Pornchai
    ;
    Tsugawa, Takuya
    ;
    Maruyama, Takashi
    ;
    Nagatsuma, Tsutomu
    The equatorial spread-F (ESF) is a phenomenon of ionopheric irregularities which are mainly generated by the generalized Rayleigh-Taylor (R-T) instability mechanism in conjunction with the other physical mechanisms, originated at the bottom side of the F-layer in the equatorial region after sunset. It degrades the quality of signals that propagate through these irregularities, especially in the navigation satellite system, which requires the high integrity signals. In this work, we analyze the ESF statistics obtained from the FM/CW ionosonde stations over Thailand longitude sector. One is at Chumphon (10.72 N, 99.37 E, dip latitude 3.0), located near the geomagnetic equator, and the other station is located at Chiangmai (18.76 N, 98.93 E, dip latitude 12.7). Both stations are as part of the South-East Asia Low Latitude Ionospheric Network (SEALION) project. The ionograms are obtained at every 15 min from September 2004 to August 2005, which has the monthly mean of solar 10.7 cm flux (F10.7) from ∼80 to ∼110. In addition, we compare the diurnal patterns between the ESF occurrences and the variation of virtual height of the F-layer bottom side (h'F) of these two stations. The results show that the ESF occurrences at Chumphon stations are higher than Chiangmai station in all seasons. The high ESF occurrences of both stations mostly occur in equinoctial months corresponded with the rapid rising of the monthly mean h'F in the post-sunset. However, some inconsistent results are still observed, implying the role of other factors such as gravity waves and planetary waves to ESF occurrences. © 2012 COSPAR. Published by Elsevier Ltd. All rights reserved.