Publications and Resources

Autonomous sampling machines need the ability to target samples despite limited visibility and robotic arm reach distance. We design a method to speed up the search process.

Noblis developed algorithm and system that simplifies, automates and quantifies interpretation of tests to help improve biothreat detection in resource-constrained environments.

Our research underscores the importance of understanding atmospheric and surface condition evolution in identifying early signals for wildfire occurrence. These findings are being used to inform the development of an AI/ML-based early warning system.

Loop-mediated isothermal amplification (LAMP) assays provide a rapid and cost-effective means for detection at point-of-care. Noblis-developed algorithm and simple analysis platform helps increase utility for in-field applications.

Noblis' virtual reality app allows for safe and rapid CBRN training exercises.

We show experimentally that SurfaceAug outperforms existing methods on car detection tasks and establishes a new state of the art for multimodal ground truth sampling.

Robotic access monitoring of multiple target areas has applications including checkpoint enforcement, surveillance and containment of fire and flood hazards. Through simulation we measure the performance of approaches on different scenarios.

Noblis-developed tool bridges the gap between data analysis and actionable information for vector-borne diseases.

This paper reports the results of a research study designed to assess the accuracy and reliability of forensic bullet comparison decisions, which is important to assess scientific validity for admissibility in court.

Accurate weather forecasts are crucial to planning disaster management, protecting existing infrastructure, and sustaining federal mission areas. Geospatial foundation models have been developed as impactful tools for various stakeholders as vision transformers increasingly outperform numerical weather prediction models.

This case study shows how sequence stratigraphic interpretation methods can be applied to improve groundwater remediation efficiency.

For digital twins to be able to evolve with their paired, realworld system the artifacts associated with these various disciplines must remain synchronized and coherent throughout the digital twin lifecycle. We provide a paradigm for harmonizing this multidisciplinary effort.