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 disable satellites, disrupt air navigation, cause power outages and pose a serious radiation hazard to astronauts. With humanity’s increasing dependence on space-based technology and plans for more intensive space exploration, accurate solar weather forecasting has become critical.
As humanity’s technological dependence increases, so does its sensitivity to space weather. According to a systemic risk scenario prepared by Lloyd’s, the global economy could suffer losses of 2.4 trillion US dollars over a five-year period. The threat of a hypothetical solar storm alone would result in losses of USD 17 billion. Recent solar events (1) have already highlighted this risk, disrupting GPS services, forcing flight detour and damaging satellites. The effects of solar storms can cause the following:
- Damage to satellites, spacecraft and/or injury to astronauts stationed off Earth
- Loss of satellite hardware, damage to solar panels and circuitry
- Impact on air traffic due to navigational errors, as well as a potential radiation hazard to flight crew and passengers
- Lower food production, as agriculture may be affected by GPS navigation disruptions
The implications affect both academic research and operational readiness. The new model will give experts tools to prepare for solar storms that can disrupt Earth’s technological infrastructure.
“Think of it like a space weather forecast,” says Juan Bernabe-Moreno, Director of IBM Research Europe, UK and Ireland. “Just as we prepare for dangerous weather events, we need to do the same for solar storms. Surya gives us unprecedented opportunities to anticipate what’s coming. This is not just a technological achievement, but a critical step in protecting our technological civilization from the star that sustains us.”
Conventional solar weather forecasts rely on partial satellite images of the sun’s surface, which has made accurate predictions extremely difficult in the past. Surya addresses this typical limitation by training on the largest curated high-resolution heliophysics dataset. This dataset will help researchers to better investigate and evaluate important space weather prediction tasks. Examples of such tasks for which Surya has been tested include predicting solar flares, the speed of solar winds, predicting EUV spectra of the Sun and the occurrence of active regions on the Sun.
In initial tests, the researchers report a 16 percent improvement in the accuracy of solar flare classification, which they describe as a very significant improvement over previous methods. In addition to binary classification of solar flares, Surya is designed to visually predict solar flares for the first time. It provides a high-resolution image of the location where the flare is expected to occur up to two hours later.
The technical challenges were immense. Surya was trained using nine years of high-resolution solar observation data from NASA’s Solar Dynamics Observatory. These solar images are ten times larger than typical AI training data, so a customized multi-architecture solution was required to handle the enormous 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 infusing NASA’s deep scientific expertise into cutting-edge AI models,” said Kevin Murphy, Chief Science Data Officer at NASA Headquarters in Washington. “By developing a baseline model trained on NASA’s heliophysical data, we are facilitating the analysis of the complexity of solar behavior with unprecedented speed and precision. This model enables a more comprehensive understanding of how solar activity impacts critical systems and technologies that we all rely on here on Earth.”
Surya is part of a broader initiative by IBM to pursue generative and automated approaches that enable algorithms to be discovered, tested and evolved at scale. Surya is an example of how IBM is positioning AI not just as a tool, but as a driver of scientific discovery. With the release of Surya on Hugging Face, IBM and NASA are democratizing access to advanced tools for understanding and predicting solar weather and scientific exploration. Researchers around the world can now build on this foundation to develop specialized applications for their regions and industries.
This model is part of a larger collaboration between IBM and NASA using AI technology to explore our planet and solar system. It complements the Prithvi family of base models, which also includes a geospatial model and a weather model. Last year, IBM and NASA released the Prithvi weather model on Hugging Face to help scientists and the broader public develop short- and long-term weather and climate forecasts.
About IBM
IBM is a leading provider of global hybrid cloud and AI solutions and consulting expertise. We help clients in more than 175 countries gain insights from their data, optimize business processes, reduce costs and gain a competitive advantage in their industry. Thousands of government agencies and organizations in critical infrastructure sectors such as financial services, telecommunications and healthcare rely on IBM’s hybrid cloud platform and Red Hat OpenShift to drive their digital transformation quickly, efficiently and securely. IBM’s breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting provide our clients with open and flexible options. All of this is backed by IBM’s long-standing commitment to trust, transparency, accountability, inclusion and service.
– – – – – –
Further links
👉 www.ibm.com/de-de
Photo: IBM
