SAP’s tabular AI foundation model, SAP-RPT, makes predictions directly from structured data, including with some data missing and without requiring the usual model training or fine-tuning.
Running directly onboard the ISS on HPE Spaceborne Computer-2, it supports anomaly triage in real-time telemetry data, predicts issues before failures escalate, reconstructs missing sensor values based on historical data, and generates explainable mission-health reports for astronauts and ground teams.
“This is proof that tabular AI on SAP works at the edge of possibility,” said Mayank Shrivastava, vice president of generative AI and foundation models at SAP SE.
“Space is the ultimate stress test for AI. If a foundation model can predict mission-critical failures in orbit, under radiation, energy and connectivity constraints, imagine what it can do for a global enterprise.
“This is the same model that will predict supplier risk, cash flow anomalies and equipment failures across your enterprise. What works in orbit works in your supply chain.”
SAP-RPT is part of SAP’s portfolio of tabular foundation models (TFM) that includes the TabPFN model by Prior Labs and SAP AI Core, which orchestrates, manages and governs TFMs, predictions and workflows.
Large language models (LLM) excel at language and reasoning but TFMs are built for the structured tabular data that underpin real-world operations, such as the sensor-driven data used in this project.
SAP-RPT is about 50,000 times more energy-efficient than state-of-the-art LLMs. This is especially important in space, where every watt is constrained. SAP-RPT is also highly adaptable. It requires no pre-training as conditions evolve.
Outcomes that will be delivered onboard include real-time predictions for computer and mission health status, an overall mission risk score, an assessment of whether manual intervention is needed, human-readable explanations of AI-driven findings, and ad hoc reports for crew and ground teams.
“HPE Spaceborne Computer-2 continually demonstrates the advantages of having a high-performance compute solution aboard the ISS, supporting advanced technologies and ongoing research in space,” said Scott Wiest, vice president and global sales chief technologist, HPE Fellow.
“Deploying SAP’s tabular AI on HPE Spaceborne Computer-2 shows what’s possible with real-time detection and prediction using AI in the ultimate edge environment.”
The deployment of SAP-RPT on HPE’s Spaceborne Computer-2 on the ISS, by early 2027, will show how it strengthens business functions on earth.
The constraints of space, including extreme energy limits, intermittent connectivity, radiation interference and zero tolerance for failure are relevant to challenging use cases on earth. These include disaster relief operations, agriculture in remote areas, distributed manufacturing and spread-out supply chains.
Want to see more stories from trusted news sources?Make Space Connect a preferred news source on Google.
