NASA JPL has been a leader in assessing microbial contamination risk on spacecraft to protect planetary environments. This requires analyzing microbial growth taken from samples of the spacecraft, and has recently shifted to include incorporating metagenomic data in the risk assessment to determine whether organisms can survive in extreme conditions.

The early development of this process relied on manual database queries and expert interpretation. It was slow, difficult to scale, and hard to standardize.

AISquared partnered with NASA JPL to build SPACE-CADET, an AI-driven data evaluation tool. It automates microbial risk analysis by combining metagenomic data, curated databases, and AI-based classification.

The result: faster, consistent contamination risk assessment that supports mission readiness and scientific integrity.

The Challenge

JPL scientists study microbial DNA found on spacecraft surfaces and in cleanroom environments. This plays a key role in planetary protection, ensuring that terrestrial microorganisms do not compromise extraterrestrial bodies during exploration missions. Earlier, this analysis relied on a manual lookup and evaluation process.

Key challenges included:

• Manual Data Workflows: Scientists had to query multiple databases and manually curate microbial data.
• Time-Intensive Analysis: Each evaluation required multiple steps, which needed improvements in speed to be commensurate with mission timelines.
• Fragmented Data Sources: Critical microbial information existed across separate systems.
• Inconsistent Evaluations: Risk classification depended on individual expertise, making standardization difficult.

This made it harder to deliver timely, repeatable contamination risk assessments for mission decisions.

The Solution

AISquared partnered with NASA JPL to build SPACE-CADET, an AI powered application that automates microbial contamination risk analysis. The system enables scientists to analyze microbial data quickly and receive clear risk evaluations.

• Automated Data Processing: Metagenomic datasets are ingested and processed through a unified pipeline.
• AI-Powered Risk Scorning: The application applies a microbial risk scoring model developed by CalTech, that analyses microbial metadata and maps organisms into predefined risk categories, from harmless to high risk based on your mission profile.
• Integrated Data Access: The platform connects to online databases and uses JPL-defined threat assessment metrics to evaluate survivability.
• Real-Time Insights: Researchers receive structured outputs including:
  • contamination risk levels
  • categorized organism profiles
  • summary reports for mission review
• Automated Reporting: The system generates consistent outputs that can be used across teams and missions.
• Secure by Design: The application runs through a secure browser interface with authenticated access, allowing researchers to safely run analyses and view results.

Conclusion

The collaboration between NASA JPL and AISquared demonstrates how AI can operationalize complex scientific models and make them accessible to mission teams. By transforming microbial contamination analysis into an automated application, NASA scientists can now evaluate risk faster, reduce manual analysis, and support safer space exploration missions.

With AISquared’s platform as the foundation, NASA JPL now has a scalable system for microbial risk assessment that supports planetary protection and mission readiness.