Award Data

This work will develop a real-time wildfire forecast system that automatically detects and forecasts the spread of every fire in the Continental US and updates each forecast in real-time as additional information becomes available. Fire forecast data, which are generated “in the cloud” using high performance computing resources, are transferred to a web server hosting a mobile-friendly web map ...

NanoElectronic Imaging, Inc. (NEI) is developing techniques for mapping signals in the transmission electron microscope (TEM) that are normally inaccessible. In this Phase I SBIR project, NEI will build on preliminary results to develop a quantitative, TEM-based topographic mapping technique with the potential for atomic resolution in all three spatial dimensions. This precision would be akin to a ...

We propose to demonstrate the feasibility of using a high-speed artificial intelligence (AI)-driven experimental platformto optimize the DNA template for cell-free protein synthesis (CFPS) to maximize protein expression. Our platform isdesigned to rapidly find an optimal DNA sequence among millions of possible sequences through repeated designbuild-test cycles: AI is used to design the DNA templat ...

The main focus of this SBIR Phase II project is to develop a prototype instrument and test cartridges for injectability pre-screening of high concentration protein formulations (HCFs). HCFs are non-Newtonian fluids with shear-thinning behavior and they are formulated to be administered by subcutaneous or muscular injections. The injectability and manufacturability of HCFs depend on the viscosity b ...

Vector Atomic, NIST, and OctoSig will design, build, and demonstrate a time transfer module capable of synchronizing mobile assets to better than 10 fs. The Heterodyne Integrated Photonics Package for Optical Synchronization (HIPPOS) module will use NIST’s established two-way optical time transfer scheme, which is insensitive to signal dropouts and turbulence and compensates for relative motion ...

In this proposed effort, Freedom Photonics will develop and demonstrate integrated Optical Two-Way Time and Frequency Transceiver (O-TWTFT) modules to support future deployment on mobile platforms. Freedom Photonics will leverage our high power balanced MUTC detector development and photonic integrated circuit (PIC) expertise to develop a PIC-based heterodyne linear optical detection modules and p ...

Conceptual Research Corporation proposes to expand upon the results of the Phase 1 study, in which we defined and assessed an aircraft design and fabrication process capable of reducing development time and allowing surge production of 500 air vehicles in less than two months. CRC will also continue its ongoing development of the “Flying Missile Rail” (FMR) air vehicle concept including fabric ...

DeepVerify is a suite of tools to verify and certify robustness of different types of AI applications with a specific focus on currently popular neural networks such as deep CNN, reinforcement learning, recurring neural networks. However, our tools can be deployed on other types of AI/ML frameworks as well. Upon automated in-depth assessment of AI applications and exploration of input data space a ...

This proposal outlines a proposed mathematical framework for the detection of and adaptation to novelty in online AI systems. This framework is founded on two existing theories in which GDA personnel have particular talents: shape analytics and reinforcement learning. Phase I is dedicated to performing the research necessary to develop this framework. Phase II would involve developing the algorith ...

NOAA's Big Data Project (BDP) has made several valuable datasets available on major cloud platforms. While a critical step, many organizations that would benefit from the data are not technologically capable of performing state-of-the-art machine learning. We propose to unlock the power of the data for those who can most benefit by developing technology that automatically trains deep learning mode ...