KMITL

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

Browse

Search Results

Now showing 1 - 10 of 24

Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
Corrigendum to “Spatio-temporal characteristics of ionospheric irregularities in low latitude regions during the peak of solar cycle 25” [Adv. Space Res. 76(1) (2025) 254–268, (S0273117725004168), (10.1016/j.asr.2025.04.062)]
(2025-09-01)
Tongkasem, Napat
;
Supnithi, Pornchai
;
Thammavongsy, Phimmasone
;
Nishioka, Michi
;
Perwitasari, Septi
The authors regret that the following was omitted from the acknowledgment section: This research project is also financially supported by National Research Council of Thailand (NRCT) under grant N41A640235. The authors would like to apologise for any inconvenience caused.
Some of the metrics are blocked by your
consent settings
Classification of Equatorial Ionospheric Irregularities Using Unsupervised Machine Learning Based on Spatiotemporal ROTI Keograms
(2025-01-01)
Mutasov, Gleb
;
Supnithi, Pornchai
;
Budtho, Jirapoom
;
Tongkasem, Napat
;
Nishioka, Michi
Equatorial ionospheric irregularities, particularly those associated with equatorial plasma bubbles (EPB), can significantly disrupt satellite navigation and communication systems. As the demand for reliable Global Navigation Satellite System (GNSS) and communication services grows, the prediction of ionospheric irregularities becomes critical. A key step in the prediction process is to identify distinct spatiotemporal patterns of irregularities, including day-to-day, longitudinal, and seasonal variations. However, with large datasets, manually classification or identification of these irregularities is a complex and challenging task. In this work, we propose unsupervised machine learning techniques to recognize and group irregularity patterns in large, unlabeled Rate of Total Electron Content (TEC) Index (ROTI) keograms. Specifically, two machine learning models: Gaussian Mixture Model and k-means clustering are employed. The ROTI keograms are constructed using GNSS data from two low-latitude receiver stations in Thailand. To reduce redundancy in the keogram images, three feature extraction techniques are applied before the clustering process. A comparative analysis is performed to determine the optimal number of clusters using these models. Based on the results, the optimal combination of feature extraction and clustering technique is determined for the proposed clustering model. The resulting k-means model with contour extractor classifies five distinct patterns of ionospheric irregularity patterns, providing valuable insights for enhancing EPB prediction models and deepening our understanding of ionospheric dynamics. Furthermore, these five irregularity patterns are analyzed in relation to space weather parameters such as the solar radio flux index (F10.7), and the geomagnetic index (Kp). The findings contribute to the development of robust prediction models, improving the reliability of satellite-based communication and navigation systems.
Some of the metrics are blocked by your
consent settings
Ionospheric Scintillation Prediction Using Decision Tree and Rainforest Techniques
(2024-01-01)
Trachuentong, Sirasake
;
Supnithi, Pornchai
;
Myint, Lin Min Min
;
Saito, Susumu
The ionosphere contains electron density variation. When radio signals transmitted from global navigation satellite systems (GNSS) pass through such medium, additional delays are added. With ionospheric irregularity, fluctuation in GNSS signals known as scintillation are often observed resulting in reduced number of tracked satellites then degrade positioning performances. At present, scintillation is considered random, hence, the ability to detect or predict such phenomenon is crucial to efficient system operation. In this research, we design machine learning algorithm for scintillation prediction. Both Decision Tree (DT) and Random Decision Forest (RF), are implemented to predict daily ionospheric scintillation at King Mongkut's Institute of Technology Ladkrabang (KMITL) station in Thailand (13.73 ° E, 100.77° N). The rate of total electron content change index (ROTI) is also used. Modeling is carried out for four months in March (equinox), June (solstice), September (equinox), and December (solstice) in 2022, representing different seasons in space weather study. The prediction results are evaluated using the S 4 index observations at KMITL station and then compared between DT and RF methods. The designed model has a high potential for scintillation prediction.
Some of the metrics are blocked by your
consent settings
Simultaneous equatorial plasma bubble observation using amplitude scintillations from GNSS and LEO satellites in low-latitude region
(2023-12-01)
Seechai, Khanitin
;
Myint, Lin Min Min
;
Hozumi, Kornyanat
;
Nishioka, Michi
;
Saito, Susumu
This study estimates the scale sizes of the plasma density irregularities and the longitudinal width associated with equatorial plasma bubbles (EPBs) in equatorial and low-latitude regions. By analyzing amplitude scintillation S<inf>4</inf> indices and total electron content (TEC) measured from low earth orbit (LEO) satellite’s beacon signals with 400 MHz and Global Navigation Satellite System (GNSS) L1/E1 signals with 1575.42 MHz, recorded by receivers at the KMITL station in Bangkok, Thailand (geographic; 13.73° N, 100.77°E, magnetic: 7.26°N), we investigate the characteristics of these irregularities. We collected data of 154 LEO satellite pass events during nighttime on 21 disturbed days in four equinoctial months in 2021. Based on the presence or absence of the scintillation effects on GNSS and LEO beacon signals, the events are categorized into four classes to estimate the scale size of the plasma density irregularities. The analysis suggests that events with both GNSS and LEO scintillations, as well as events with GNSS scintillation alone, occur predominantly before midnight assuming the presence of the small-scale size of the irregularities within EPB. However, events with only LEO scintillation occur throughout the whole night and some events are observed before the events with both GNSS and LEO scintillations. Post-sunset LEO scintillation alone may be attributed to the onset of EPBs developing at low altitude, while post-midnight LEO scintillation events near the magnetic equator, observed during periods of low GNSS Rate of TEC Index (ROTI) values, are associated with bottom-side ionospheric irregularities but are not linked with EPB. The findings are consistent with previous researches on the generation and decay of electron density irregularities within plasma bubbles. However, this study provides new insights by using specific data sets and analysis techniques, offering a more comprehensive understanding of the association of LEO scintillations with bottom-side ionospheric irregularities near the magnetic equator, not observed in the ROTI map. Graphical Abstract: [Figure not available: see fulltext.]
Some of the metrics are blocked by your
consent settings
Equatorial spread-F forecasting model with local factors using the long short-term memory network
(2023-12-01)
Thammavongsy, Phimmasone
;
Supnithi, Pornchai
;
Myint, Lin Min Min
;
Hozumi, Kornyanat
;
Lakanchanh, Donekeo
The predictability of the nighttime equatorial spread-F (ESF) occurrences is essential to the ionospheric disturbance warning system. In this work, we propose ESF forecasting models using two deep learning techniques: artificial neural network (ANN) and long short-term memory (LSTM). The ANN and LSTM models are trained with the ionogram data from equinoctial months in 2008 to 2018 at Chumphon station (CPN), Thailand near the magnetic equator, where the ESF onset typically occurs, and they are tested with the ionogram data from 2019. These models are trained especially with new local input parameters such as vertical drift velocity of the F-layer height (Vd) and atmospheric gravity waves (AGW) collected at CPN station together with global parameters of solar and geomagnetic activity. We analyze the ESF forecasting models in terms of monthly probability, daily probability and occurrence, and diurnal predictions. The proposed LSTM model can achieve the 85.4% accuracy when the local parameters: Vd and AGW are utilized. The LSTM model outperforms the ANN, particularly in February, March, April, and October. The results show that the AGW parameter plays a significant role in improvements of the LSTM model during post-midnight. When compared to the IRI-2016 model, the proposed LSTM model can provide lower discrepancies from observational data. Graphical Abstract: [Figure not available: see fulltext.].
Some of the metrics are blocked by your
consent settings
Classification of the equatorial plasma bubbles using convolutional neural network and support vector machine techniques
(2023-12-01)
Thanakulketsarat, Thananphat
;
Supnithi, Pornchai
;
Myint, Lin Min Min
;
Hozumi, Kornyanat
;
Nishioka, Michi
Equatorial plasma bubble (EPB) is a phenomenon characterized by depletions in ionospheric plasma density being formed during post-sunset hours. The ionospheric irregularities can lead to disruptions in trans-ionospheric radio systems, navigation systems and satellite communications. Real-time detection and classification of EPBs are crucial for the space weather community. Since 2020, the Prachomklao radar station, a very high frequency (VHF) radar station, has been installed at Chumphon station (Geographic: 10.72° N, 99.73° E and Geomagnetic: 1.33° N) and started to produce radar images ever since. In this work, we propose two real-time plasma bubble detection systems based on support vector machine techniques. Two designs are made with the convolutional neural network (CNN) and singular value decomposition (SVD) used for feature extraction, the connected to the support vector machine (SVM) for EPB classification. The proposed models are trained using quick look (QL) plot images from the VHF radar system at the Chumphon station, Thailand, in 2017. The experimental results show that the combined CNN-SVM model, using the RBF kernel, achieves the highest accuracy of 93.08% while the model using the polynomial kernel achieved an accuracy of 92.14%. On the other hand, the combined SVD-SVM models yield the accuracies of 88.37% and 85.00% for RBF and polynomial kernels of SVM, respectively. Graphical Abstract: [Figure not available: see fulltext.].
Some of the metrics are blocked by your
consent settings
Instrumental Receiver Bias Estimation for Ionospheric Total Electron Content by Neural Network Model
(2023-10-01)
Thu, Phyo C.
;
Supnithi, Pornchai
;
Budtho, Jirapoom
;
Saekow, Apitep
;
Sopon, Thanomsak
Total Electron Content (TEC) is one of the most important parameters in the study of the ionosphere, especially for determining ionospheric disturbances. The TEC levels are typically estimated from dual-frequency GPS observation data. Since the measured TEC contains discrepancies such as satellite and receiver biases, they need to be removed to obtain more accurate TEC values. In this work, we estimate the receiver bias using a neural network technique. Based on the exhaustive evaluation, we design a neural network (NN) model with two-hidden layers, and it is trained with datasets from three GNSS observation stations in Thailand. The prediction from the proposed neural network deviates from the baseline reference using the minimum standard deviation method with significantly faster computational time. The trained NN model is also tested for estimating the receiver bias values at other untrained stations in Thailand.
Some of the metrics are blocked by your
consent settings
Investigating the F2-layer peak height of IRI-2016 model at the equatorial station during the deepest solar activity for 70 years ago
(2023-01-01)
Jamjareegulgarn, Punyawi
;
Taugtragoonpaisan, Udomsit
;
Myint, Lin Min Min
;
Supnithi, Pornchai
The paper investigates the F2-layer peak height (hmF2) of IRI-2016 model at Sao Luis on the magnetic Equator in 2019. Since the deepest solar activity occurred surprisingly in year 2019 for 70 years ago, hence, the IRI-2016 model prediction should be investigated to know the anomalous ionosphere and the deviations between the observation and IRI prediction. The hmF2 is selected to be studied in this work. Our studied results show that the observed hmF2 and the three hmF2 models of IRI-2016 prediction generally show the similar variations only about 60% during this deepest solar activity and the variations of the four kinds of studied hmF2 values show the similar trends for all seasons, except June solstice. The diurnal variation of hmF2_Giro show three peaks for December solstice months and the equinoctial months, while they show four peaks amazingly in June solstice. The hmF2_SHU is the best option that can agree reasonably well to the observed hmF2 at Sao Luis, excluding the pre-sunrise hmF2 peak for all seasons and a very deep trough in June solstice.
Some of the metrics are blocked by your
consent settings
Equatorial Plasma Bubble Detection using the Convolutional Neural Network (CNN) and Support Vector Machine (SVM)
(2023-01-01)
Thanakulketsarat, Thananphat
;
Supnithi, Pornchai
;
Myint, Lin Min Min
;
Hozumi, Kornyanat
Equatorial plasma bubbles (EPB) refer to the area of low electron density in the Earth's ionosphere near the equator during post sunset and post-midnight. They influence the radio communications and GPS signals. In this work, we study the EPB occurrences and characteristics using the VHF radar images observed at the Chumphon station, Thailand, near the magnetic equator.. We develop an EPB image detection system using a hybrid learning technique with convolutional neural network (CNN) and support vector machine (SVM) and evaluate the accuracy of the proposed CNN-SVM model using two kernels: polynomial kernel and radial basis function (RBF) kernel.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results