Award Data

Machine learning algorithms have demonstrated performance on par with or superior to human analysts on large datasets when sufficient training data is available.  For military applications obtaining sufficient, truthed data is always a challenge.  Three approaches have been used for measured data collections to support sensor exploitation programs: coordinated collections, turntable measurements ...

The Defense Threat Reduction Agency (DTRA) needs a capability to collect and provide immediate presumptive analysis of radiological/nuclear samples of concern at the source of collection. Such in-field technologies should be capable of detecting and identifying trace quantities of elements and/or chemicals containing plutonium (Pu) and uranium (U), with a focus on chemicals specific to the nuclear ...

For effective protection against radiated threats, produced by high altitude electromagnetic pulse (HEMP) caused by nuclear detonations and high-power microwave (HPM) Directed Energy (DE) weapons it is important to understand not only the physics of the threats, but also to quantify the effects on mission-critical electrical systems. EMP/HMP simulators enable threat level testing of MCS and provid ...

Deep Convolutional Neural Networks (DCNNs) have become ubiquitous in the analysis of large datasets with geometric symmetries. These datasets are common in medicine, science, intelligence, autonomous driving and industry. While analysis based on DCNNs have proven powerful, uncertainty estimation for such analyses has required sophisticated empirical studies. This has negatively impacted the effect ...

The Synthetic Aperture Radar (SAR) Image Generation Data Augmentation (SIGDA) system is achieved using SAR simulators and the Arete’s Reification approach. Large, realistic datasets will be generated using the Arete Reification capability. These large Reified datasets are then used to train machine learning or Artificial Intelligence (AI), Automatic Target Recognition (ATR) classification algori ...

Machine learning algorithms have demonstrated performance on par with or superior to human analysts on large datasets when sufficient training data is available. For many military applications, sufficient truthed data over relevant operating conditions does not exist and is prohibitively expensive to obtain. A potential solution to thislack of measured datais synthetic data derived from physics si ...

The overall goal is to develop numerics-informed neural networks (NINNs) and DeepOnets for chemical reactions and for PDEs with spatial derivatives improve the computational efficiency of the chemical kinetics models for chemical weapon agents and simulants. Based on the first NINN developed by the Karniadakis’s group in 2018, which blends the multi-step time-stepping with deep neural networks, ...

The team of Signature Research, Inc. and Michigan Technological University will develop and demonstrate methods and metrics to evaluate the performance of machine learning-based computer vision algorithms with low numbers of samples of labeled EO imagery. We will use the existing xView panchromatic dataset to demonstrate a proof-of-concept set of tools. If successful, in Phase II, we will extend t ...

Low-shot objection recognition has become an area of active research in recent years, with advances dramatically improving performance when only a few samples are available, nominally fewer than 20. These technologies are a focus of the intelligence community (IC) because this challenge pertains to many intelligence problems, e.g., objects of interest are rare due to their use, sensitive nature, ...

Improving the effectiveness of counter-WMD operations requires improved understanding of weapon-target interaction. Specifically, time-resolved measurements of temperature and composition are required to allow temporal evolution of a detonation fireball. To address this need, SA Photonics will develop MONITOR, a laser-based temperature diagnostic which will enable wide dynamic range temperature me ...