7–11 September 2026 | Seoul, Republic of Korea
I am truly honoured and grateful to have had the wonderful opportunity to participate and present my research at the United Nations/Republic of Korea Workshop on the International Space Weather Initiative (ISWI) 2026, held in Seoul, South Korea, from 7 to 11 September 2026.
The workshop, themed “AI-Enabled Space Weather for Global Cooperation & Capacity Building,” was co-organized by the United Nations Office for Outer Space Affairs (UNOOSA) and the Korea Space Weather Center (KSWC) of the Korea AeroSpace Administration (KASA). It brought together researchers, scientists, and experts from around the world to share their knowledge and experiences in space weather research, particularly the growing applications of artificial intelligence.
Sharing My Research on an International Platform
I was privileged to present my research entitled: “Cross-Station Generalization and Event-Based Forecasting Skill of Deep Learning Models for Low-Latitude Geomagnetically Induced Current Prediction.”
My research explores how artificial intelligence can help predict disturbances in Earth's magnetic field caused by solar activity. These disturbances can generate electrical currents that may affect power systems and other important infrastructure.
In this study, I evaluated three deep learning models (LSTM, BiLSTM, and GRU) using magnetic field data from four locations: Peru, Senegal, India, and Guam. The findings highlight the challenges of predicting magnetic disturbances across different geographical locations, particularly during stronger events. The research also emphasizes the importance of developing more reliable forecasting approaches to help protect electrical infrastructure, especially in regions near the equator.
Meeting Inspiring Researchers and Making New Connections
One of the most meaningful parts of this experience was the opportunity to meet so many wonderful people, fellow researchers, and experts who share the same passion for space weather research.
A particularly special moment for me was meeting Dr. Richard Marshall, one of the researchers whose work I had cited and referred to during my thesis journey. It was such a memorable experience to finally meet in person someone whose research had contributed to my own academic work. Reading someone's publications is one thing, but having the opportunity to meet and exchange ideas with the researcher is truly something special!
I was also fortunate to attend this workshop together with my research team member, Dr. Zatul Iffah Ab Latiff. Sharing this international research experience together made the journey even more meaningful and enjoyable.
During the workshop, I was delighted to meet fellow Malaysian researchers, including Dr. Roslan from Universiti Sultan Zainal Abidin (UniSZA) and Dr. Nor Hazmin Sabri from Universiti Malaysia Terengganu (UMT). It was wonderful to connect with researchers from other Malaysian universities, share our research interests, exchange experiences, and build friendships along the way.
Beyond the technical sessions and presentations, the conversations, new friendships, and connections made throughout the workshop were just as valuable. It reminded me that research is not only about data, models, and publications, but also about the people we meet, the knowledge we share, and the collaborations we build.
A Meaningful Milestone in My Research Journey
I am especially grateful to the United Nations Office for Outer Space Affairs (UNOOSA) and the workshop organizing committee for the invitation and financial support that made my participation possible.
This workshop was not only an opportunity to present my research internationally but also a chance to learn from leading experts, gain new perspectives, and explore potential future research collaborations.
I am proud to have represented the Faculty of Electrical Engineering, Universiti Teknologi MARA (UiTM), Johor Branch, Malaysia, at this international event. I would also like to express my heartfelt appreciation to my Head of Department and the management of UiTM for their continuous encouragement, support, and for giving me the opportunity to participate in this international workshop.
My heartfelt thanks to my research supervisors, Dr. Muhammad Asraf Hairuddin, Prof. Mohamad Huzaimy Jusoh, and Prof. Ahmad Ihsan Mohd Yassin, for their continuous guidance, encouragement, and invaluable support throughout my research journey. I am truly grateful for their mentorship, which has helped me grow and progress in my research field.
The experience has further motivated me to continue exploring artificial intelligence applications in space weather forecasting, particularly for low-latitude regions such as Malaysia.
Looking back, ISWI 2026 was much more than a research workshop. It was an inspiring journey filled with knowledge, meaningful discussions, wonderful people, new friendships, and unforgettable memories.
From reading researchers' work in my thesis to meeting them in person, from developing research ideas to sharing my findings on an international platform — this experience is truly one of the highlights of my academic journey.
Alhamdulillah, I am grateful for this wonderful opportunity and look forward to more learning, collaborations, and research adventures ahead!
ISWI 2026 | Seoul, South Korea | Space Weather | Artificial Intelligence | Research Collaboration | UiTM Malaysia
Scientific Abstract Geomagnetically Induced Currents (GICs) threaten power infrastructures, particularly in low-latitude regions with limited geomagnetic and conductivity data. This study evaluates the sensitivity of deep learning models; LSTM, BiLSTM, and GRU, to geomagnetic longitude and solar wind variations for one-minute-ahead dB/dt forecasting at Huancayo (HUA) and Guam (GUA). Using OMNIWeb and SuperMAG datasets from Solar Cycles 23–24, models were assessed with both continuous metrics (RMSE, MAE, MAPE) and rare-event detection statistics (F1, TSS, HSS). BiLSTM achieved the best local accuracy (RMSE = 0.0169 at HUA), while GRU exhibited greater cross-station transferability (RMSE = 0.0239, MAPE = 0.0645). Performance declined at higher event thresholds, revealing difficulty in generalizing extreme event prediction across longitudes. The results show that HUA exhibits more complex geomagnetic variability than GUA, and GRU offers better adaptability across regions. Future forecasting models should integrate hybrid architectures and multi-location training to enhance low-latitude GIC prediction.
Aznilinda Zainuddin¹, Muhammad Asraf Hairuddin¹, Mohd Helmy Hashim², Akimasa Yoshikawa³, Mohamad Huzaimy Jusoh⁴, Ahmad Ihsan Mohd Yassin⁴.
¹Faculty of Electrical Engineering, Universiti Teknologi MARA, Johor Branch, Pasir Gudang Campus, Masai, Malaysia.
²Faculty of Electrical Engineering, Universiti Teknologi MARA, Shah Alam, Malaysia; Space Science and Exploration Division, Malaysian Space Agency, Banting, Malaysia.
³International Research Center for Space and Planetary Environmental Science (iSPES), and Department of Earth and Planetary Sciences, Kyushu University, Fukuoka 819-0395, Japan.
⁴Faculty of Electrical Engineering, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia.
DOI: 10.1109/ISWTA68114.2025.11329867
Method flow in developing the model.
Non-Scientist Abstract: Solar storms can affect Earth's magnetic field and create electrical currents that may disrupt power systems. These effects are less understood in regions near the equator. This study looks at how solar wind conditions and geographical locations influence the accuracy of artificial intelligence (AI) models in predicting magnetic disturbances. Three AI models, LSTM, BiLSTM, and GRU, were tested using data from Huancayo, Peru, and Guam. The results show that BiLSTM gave the most accurate predictions for Huancayo, while GRU performed better when used to predict disturbances at different locations. However, all models struggled to predict stronger and less common magnetic disturbances. The study also found that magnetic activity in Huancayo is more complex than in Guam. Overall, these findings show that AI can help improve predictions of magnetic disturbances and reduce risks to power systems. Using data from more locations could make future predictions more accurate and reliable.
Scientific Abstract Geomagnetic storms pose significant risks to technological systems on Earth. One of the ways to identify the level of a storm is from the Sym-H plot images. The fewer features used for image interpretation, the simpler and more efficient the analysis becomes. In this study, we applied Principal Component Analysis (PCA) to the Sym-H index images, initially consisting of seven statistical features. Through PCA, this study managed to reduce these features to just two principal components, capturing over 98% of the total variance in the first two components, thereby retaining essential information while simplifying the dataset. This reduction not only simplifies the visualization and interpretation of the Sym-H plot images but also retains the critical information necessary for understanding geomagnetic storm dynamics. By focusing on these two principal components, we can effectively present and analyse the essential patterns and behaviours of geomagnetic activity during storm events. The findings highlight the potential of PCA to enhance space weather forecasting and improve the resilience of technological infrastructure against solar storm impacts.
Aznilinda Zainuddin¹, Muhammad Asraf Hairuddin¹, Zatul Iffah Abd Latiff¹, Nur Dalila Khirul Ashar¹, Anwar Santoso², Mohamad Huzaimy Jusoh³, Ahmad Ihsan Mohd Yassin³.
¹Electrical Engineering Studies, College of Engineering, Universiti Teknologi MARA, Johor Branch, Pasir Gudang Campus, Malaysia.
²Center for Space, National Research and Innovation Agency, Bandung, Indonesia.
³School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA, Shah Alam, Malaysia.
http://dx.doi.org/10.37231/myjas.2025.10.1.432
Principal Component Analysis (PCA) results of Sym-H index features.
Non-Scientist Abstract: Storms from the Sun, known as geomagnetic storms, can disrupt many technologies we rely on here on Earth. To understand how strong these storms are, scientists often look at images called Sym-H plots. Normally, these images involve several features that need to be studied, but using too many details can complicate the process. In this work, we used a method called Principal Component Analysis (PCA) to simplify the data. We started with seven different features and managed to reduce them to just two key ones, without losing important information. These two features alone explained almost all of the patterns found in the original data. This makes the storm images easier to interpret while still showing the main storm behaviours. The results show that simplifying the data in this way can help us better understand geomagnetic storms, which may also support efforts to improve space weather forecasting and protect our everyday technologies from solar impacts.
Scientific Abstract Space weather (SpW) is a phenomenon caused by a variety of solar events and has the potential to disrupt infrastructure systems and technology, putting them at risk. Despite SpW’s immense impact, there has been a notable absence of bibliometric analysis studies to understand the research trends, regional distribution, social structure, conceptual structure, and knowledge gaps. This review synthesized scopus documents of SpW domain from 1988 to 2021. In this study, three tools were used, such as Microsoft Excel, VOSviewer, and Harzing’s Publish or Perish for statistical analysis, graphical presentation, and citation metrics, respectively. Based on the 3,956 articles, roughly 70% of the articles were published in the last ten years, reveals a rapid growth in SpW research. The study discovered that China ranked third in publication volume, following the United States and the United Kingdom with Russian Federation following closely in fourth place. This study also presents six key findings, including the growth pattern of publications, contributions, and authorship collaboration by countries, most productive and influenced authors, co-authorship status, most influenced journals and articles, research cluster and new SpW subtopics discovered. These findings provide useful insight and aid in the advancement and progress of this field.
Zainuddin, A., Hairuddin, M. A., Iffah, Z., Latiff, A., & Anuar, N. M. (2021). An Overview of 33 Years of Trends in Space Weather Research : A Bibliometric Analysis ( 1998 ‐ 2021 ). https://doi.org/10.11591/eei.v14i1.8159
Citations by year and growth trajectory on SpW publications, 1988-2021 (n=3,956)
Non-Scientist Abstract: Space weather, caused by solar activity, can disrupt technologies like satellites, power grids, and communication systems. Despite its growing impact, there's been little research analyzing overall trends in this field. This study reviewed nearly 4,000 space weather papers from 1988 to 2021 using tools like Excel, VOSviewer, and Publish or Perish. Findings show rapid research growth—70% of articles were published in the last decade. The U.S. and U.K. lead in output, followed by China and Russia. The study highlights key trends in collaboration, influential authors, research clusters, and emerging topics, offering insights to guide future space weather research and development.
Scientific Abstract: Space weather, caused by solar storms, can disrupt Earth’s magnetic field and generate electric currents known as geomagnetically induced currents (GICs). These currents can damage power grids, pipelines, and communication systems. While GICs are commonly studied in higher-latitude countries, their effects in low-latitude regions closer to the equator are less understood. This study aims to predict GICs in three low-latitude locations: Huancayo (Peru), Addis Ababa (Ethiopia), and Guam (USA). The researchers used artificial intelligence models called LSTM and BiLSTM, which are designed to recognize time-based patterns. These models were trained on space weather data from a major solar storm on 31 March 2001, including solar wind speed, pressure, magnetic field strength, and geomagnetic activity. A key measurement used in this study was the rate of change in Earth’s magnetic field, which closely relates to GIC strength. The study found that organizing the training data into continuous blocks significantly improved the models’ accuracy by up to 66% compared to traditional methods. However, traditional methods were better for event-specific predictions. These findings show that AI can help predict space weather impacts even in areas where GIC research is limited, supporting better protection of critical infrastructure worldwide.
Zainuddin, A., Hairuddin, M. A., Iffah, Z., Latiff, A., Anuar, N. M., Benavides, I. F., Jusoh, M. H., Ihsan, A., & Yassin, M. (2024). Prediction of geomagnetically induced currents in low-latitude regions using deep learning. October. https://doi.org/10.18520/cs/v127/i6/691-700
Data used for the model development are taken from the low-latitude region with geomagnetic location between –30° and +30°.
Non-Scientist Abstract: This study introduces a model to predict geomagnetically induced currents (GICs), electric currents caused by space weather, that can affect power systems. The model focuses on three low-latitude locations: Huancayo (Peru), Addis Ababa (Ethiopia), and Guam (USA). It uses advanced types of artificial intelligence (AI) called LSTM and BiLSTM, which are good at spotting patterns over time. The model was tested using real data from a space weather event in March 2001. Results showed that a specific way of organizing the data improved prediction accuracy by up to 66%. However, a traditional testing method still worked better for checking accuracy during single events.
Aurora Cahaya Indah di Langit
My article titled "Aurora Cahaya Indah di Langit" being published in Dewan Kosmik.
In this piece, I explain how auroras are formed and whether they pose any harm to humans. You can read it in the latest issue of Dewan Kosmik—get your copy now!
Sains di Sebalik Fenomena Arus Teraruh Geomagnet
I'm excited to share that my article titled "Sains di Sebalik Fenomena Arus Teraruh Geomagnet" is featured in the August 2024 issue of Dewan Kosmik! In this piece, I dive into the fascinating science behind geomagnetically induced currents (GIC) and their impact on modern technology.
Don't miss it! Grab your copy now!
Ilmu Sains Cuaca Angkasa Membentuk Generasi Sains dan Jurutera
Saya sangat teruja untuk berkongsi bahawa artikel saya yang berjudul "Ilmu Sains Cuaca Angkasa Membentuk Generasi Sains dan Jurutera" diterbitkan dalam keluaran Oktober 2025 majalah Dewan Siswa! Dalam artikel ini, saya membincangkan betapa pentingnya ilmu sains cuaca angkasa dalam membentuk generasi saintis dan jurutera masa depan. Jom baca dan fahami lebih lanjut bagaimana pendidikan STEM boleh membekalkan kemahiran penting untuk menghadapi cabaran abad ke-21!
Jangan lepaskan peluang ini! Dapatkan salinan anda sekarang!