IBM and NASA Release Groundbreaking Open-Source AI Model on Hugging Face to Predict Solar Weather and Help Protect Critical Technology
IBM (NYSE:IBM) and NASA have unveiled Surya, a groundbreaking open-source AI foundation model designed to predict solar weather and protect Earth's technology infrastructure. The model, trained on 9 years of high-resolution solar observation data from NASA's Solar Dynamics Observatory, demonstrates a 16% improvement in solar flare classification accuracy.
Named after the Sanskrit word for Sun, Surya can predict solar flares up to two hours in advance and help safeguard critical systems like GPS navigation, power grids, and telecommunications from solar storms. According to Lloyd's, solar storms could expose the global economy to potential losses of $2.4 trillion over five years, with an expected loss of $17 billion.
The model is now openly available on Hugging Face, allowing researchers worldwide to advance solar weather prediction research and develop specialized applications.
IBM (NYSE:IBM) e la NASA hanno presentato Surya, un innovativo modello fondazionale di intelligenza artificiale open source pensato per prevedere il meteo solare e proteggere le infrastrutture tecnologiche terrestri. Il modello, addestrato su 9 anni di dati di osservazione solare ad alta risoluzione provenienti dall'SDO di NASA, mostra un miglioramento del 16% nella precisione della classificazione delle eruzioni solari.
Chiamato con il nome sanscrito del Sole, Surya è in grado di prevedere le esplosioni solari fino a due ore di anticipo e di contribuire a proteggere sistemi critici come la navigazione GPS, le reti elettriche e le telecomunicazioni dagli effetti delle tempeste solari. Secondo Lloyd's, le tempeste solari potrebbero esporre l'economia globale a perdite potenziali di 2,4 trilioni di dollari in cinque anni, con una perdita attesa di 17 miliardi di dollari.
Il modello è ora disponibile pubblicamente su Hugging Face, consentendo ai ricercatori di tutto il mondo di progredire nella previsione del meteo solare e di sviluppare applicazioni specializzate.
IBM (NYSE:IBM) y la NASA han presentado Surya, un innovador modelo fundacional de IA de código abierto diseñado para predecir el clima solar y proteger la infraestructura tecnológica de la Tierra. El modelo, entrenado con 9 años de datos de observación solar de alta resolución del Solar Dynamics Observatory de la NASA, muestra una mejora del 16% en la precisión de clasificación de las erupciones solares.
Nombrado con la palabra sánscrita para Sol, Surya puede predecir las erupciones solares con hasta dos horas de antelación y ayudar a salvaguardar sistemas críticos como la navegación GPS, las redes eléctricas y las telecomunicaciones frente a las tormentas solares. Según Lloyd's, las tormentas solares podrían exponer a la economía global a pérdidas potenciales de 2,4 billones de dólares en cinco años, con una pérdida esperada de 17.000 millones de dólares.
El modelo está ahora disponible abiertamente en Hugging Face, permitiendo a investigadores de todo el mundo avanzar en la predicción del clima solar y desarrollar aplicaciones especializadas.
IBM (NYSE:IBM)과 NASA가 Surya를 공개했습니다. Surya는 태양 기상을 예측하고 지구의 기술 인프라를 보호하기 위해 고안된 획기적인 오픈소스 AI 기반 모델입니다. 이 모델은 NASA의 태양 관측 위성(Solar Dynamics Observatory)으로부터 얻은 9년간의 고해상도 태양 관측 데이터로 학습되었으며, 태양 플레어 분류 정확도가 16% 향상된 것으로 나타났습니다.
산스크리트어로 태양을 뜻하는 이름을 가진 Surya는 태양 플레어를 최대 두 시간까지 사전 예측할 수 있어 GPS 항법, 전력망, 통신 등 중요한 시스템을 태양 폭풍으로부터 보호하는 데 도움을 줍니다. Lloyd's에 따르면 태양 폭풍은 향후 5년간 전 세계 경제에 최대 2.4조 달러의 잠재적 손실을 초래할 수 있으며, 예상 손실은 170억 달러입니다.
이 모델은 현재 Hugging Face에 공개되어 전 세계 연구자들이 태양 기상 예측 연구를 발전시키고 특화된 애플리케이션을 개발할 수 있게 되었습니다.
IBM (NYSE:IBM) et la NASA ont dévoilé Surya, un modèle fondamental d'IA open source révolutionnaire conçu pour prévoir le temps solaire et protéger les infrastructures technologiques terrestres. Le modèle, entraîné sur 9 ans de données d'observation solaire en haute résolution du Solar Dynamics Observatory de la NASA, affiche une amélioration de 16 % de la précision dans la classification des éruptions solaires.
Nommé d'après le mot sanskrit pour Soleil, Surya peut prédire les éruptions solaires jusqu'à deux heures à l'avance et aider à protéger des systèmes critiques tels que la navigation GPS, les réseaux électriques et les télécommunications contre les tempêtes solaires. D'après Lloyd's, les tempêtes solaires pourraient exposer l'économie mondiale à des pertes potentielles de 2,4 000 milliards de dollars sur cinq ans, avec une perte attendue de 17 milliards de dollars.
Le modèle est désormais disponible publiquement sur Hugging Face, permettant aux chercheurs du monde entier de faire progresser la prévision du temps solaire et de développer des applications spécialisées.
IBM (NYSE:IBM) und die NASA haben Surya vorgestellt, ein bahnbrechendes Open-Source-KI-Grundmodell zur Vorhersage der Sonnenwetterlage und zum Schutz irdischer Technologieinfrastrukturen. Das Modell wurde mit 9 Jahren hochauflösender Sonnenbeobachtungsdaten des Solar Dynamics Observatory der NASA trainiert und zeigt eine 16%ige Verbesserung der Genauigkeit bei der Klassifikation von Sonneneruptionen.
Benannt nach dem Sanskrit-Wort für Sonne, kann Surya Sonneneruptionen bis zu zwei Stunden im Voraus vorhersagen und dazu beitragen, kritische Systeme wie GPS-Navigation, Stromnetze und Telekommunikation vor Sonnenstürmen zu schützen. Laut Lloyd's könnten Sonnenstürme die Weltwirtschaft über fünf Jahre hinweg potenziell mit Verlusten von 2,4 Billionen US-Dollar konfrontieren, bei einem erwarteten Verlust von 17 Milliarden US-Dollar.
Das Modell ist jetzt offen auf Hugging Face verfügbar, sodass Forschende weltweit die Sonnenwettervorhersage vorantreiben und spezialisierte Anwendungen entwickeln können.
- Achieved 16% improvement in solar flare classification accuracy compared to previous methods
- First-ever capability to visually predict solar flares up to two hours in advance
- Open-source availability on Hugging Face democratizes access for global researchers
- Trained on unprecedented 9-year high-resolution solar observation dataset
- Potential to help protect global infrastructure worth trillions from solar storm damage
- Solar storms could expose global economy to $2.4 trillion in losses over five years
- Current technological infrastructure remains vulnerable to solar weather events
Insights
IBM and NASA's new Surya AI model enhances solar storm prediction, protecting critical infrastructure while advancing IBM's position in scientific AI applications.
IBM and NASA have launched Surya, an open-source AI foundation model that represents a significant technological advancement in solar weather prediction. This innovation addresses a critical vulnerability in our technological infrastructure - one that could potentially cost the global economy
The model's technical achievements are notable. Trained on nine years of high-resolution data from NASA's Solar Dynamics Observatory, Surya processes images 10 times larger than typical AI training data, requiring custom architecture solutions. Early testing shows a
What makes this particularly valuable is the practical application to critical infrastructure protection. Solar storms can disrupt satellites, GPS navigation, power grids, and telecommunications - systems our modern economy increasingly depends upon. By making this technology open-source on Hugging Face, IBM is democratizing access to advanced predictive tools while positioning itself at the intersection of AI and scientific discovery.
This release fits strategically within IBM's broader AI portfolio, joining the Prithvi family of foundation models for geospatial and weather applications. By addressing high-stakes scientific challenges through AI, IBM is demonstrating practical applications of its AI capabilities beyond enterprise solutions, potentially opening new markets while enhancing its reputation for innovation in mission-critical domains.
The first heliophysics AI foundation model trained on high resolution solar observation data offers insights into the Sun's dynamic surface, helping plan for solar weather that can disrupt technology on Earth and in space
Openly available on Hugging Face, the model was built to speed up scientific discovery and democratize AI for the global research and technology community
Researchers also release the largest known curated heliophysics dataset to advance data driven space weather research
The Sun may be 93 million miles away, but its impact on modern life is immediate and growing. Solar flares and coronal mass ejections can knock out satellites, disrupt airline navigation, trigger power blackouts, and pose serious radiation risks to astronauts. With humanity's increasing dependence on space-based technology and plans for deeper space exploration, accurate solar weather prediction has become critical.
As humanity's technological dependence grows, so does our vulnerability to space weather. According to a systemic risk scenario created by Lloyd's, the global economy could be exposed to losses of
- Damage to satellites, spacecraft and/or astronauts that are stationed beyond Earth
- Loss of satellite hardware, damaging solar panels and circuits
- Impact to airline travel, due to navigational errors and potential risk of radiation for airline crew and passengers
- Lowered food production as agriculture can be impacted by disrupted GPS navigation
The implications include both academic research and operational preparedness. The new model will provide tools to help experts plan for solar storms, which can disrupt the Earth's technological infrastructure.
"Think of this as a weather forecast for space," said Juan Bernabe-Moreno, Director of IBM Research Europe,
Traditional solar weather prediction relies on partial satellite views of the Sun's surface, historically making accurate forecasting extremely difficult. Surya addresses this typical limitation by training on the largest curated high resolution heliophysics dataset. This dataset is designed to help researchers better study and evaluate critical space weather prediction tasks. Examples of these tasks, which Surya has been tested on, include predicting solar flares, the speed of solar winds, solar EUV spectra prediction and the emergence of active regions on the Sun.
In early testing, researchers report achieving a 16 percent improvement in solar flare classification accuracy, which researchers report as a very substantial improvement compared to previous methods. In addition to the binary solar flare classification task, Surya is built to visually predict solar flares for the first time, providing a high resolution image of where the flare is predicted to occur up to two hours out.
The technical challenges were immense. Surya was trained on nine years of high-resolution solar observation data from NASA's Solar Dynamics Observatory. These solar images are 10 times larger than typical AI training data, requiring a custom multi-architecture solution to handle the massive scale while maintaining efficiency. The result is a model with unprecedented spatial resolution that can resolve solar features at scales and contexts not previously captured in large-scale AI training workflows.
"We are advancing data-driven science by embedding NASA's deep scientific expertise into cutting-edge AI models," said Kevin Murphy, chief science data officer at NASA Headquarters in
Surya is part of a broader effort at IBM to embrace generative and automated approaches that empower algorithms to be discovered, tested, and evolved at scale. Surya is one example of how IBM is positioning AI not just as a tool, but as a driver of scientific discovery. By releasing Surya on Hugging Face, IBM and NASA are democratizing access to advanced tools for understanding and forecasting solar weather and scientific exploration. Researchers worldwide can now build upon this foundation to develop specialized applications for their regions and industries.
This model is part of a larger collaboration between IBM and NASA to use AI technology to explore our planet and solar system. It joins the Prithvi family of foundation models, which includes a geospatial model and a weather model. Last year, IBM and NASA released the Prithvi weather model on Hugging Face for scientists and the broader community to develop short- and long-term weather and climate projections.
About IBM
IBM is a leading provider of global hybrid cloud and AI, and consulting expertise. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Thousands of government and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM's hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM's breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting delivers open and flexible options to our clients. All of this is backed by IBM's long-standing commitment to trust, transparency, responsibility, inclusivity and service.
Media Contact
Ashley Peterson
IBM Research Communications
Ashley.peterson@ibm.com
1 Interplanetary Causes and Impacts of the 2024 May Superstorm on the Geosphere: An Overview – IOPscience. Interplanetary Causes and Impacts of the 2024 May Superstorm on the Geosphere: An Overview, Hajra, Rajkumar, Tsurutani, Bruce Tsatnam, Lakhina, Gurbax Singh, Lu, Quanming, Du, Aimin. https://iopscience.iop.org/article/10.3847/1538-4357/ad7462/meta
View original content to download multimedia:https://www.prnewswire.com/news-releases/ibm-and-nasa-release-groundbreaking-open-source-ai-model-on-hugging-face-to-predict-solar-weather-and-help-protect-critical-technology-302534613.html
SOURCE IBM
FAQ
What is IBM's Surya AI model and what does it do?
How much financial damage can solar storms cause to the global economy?
Where can researchers access IBM's Surya solar weather prediction model?
What types of technology can be affected by solar storms?
How was IBM's Surya AI model trained?
