Award Data

TECHNICAL ABSTRACT: Ship groundings can cause sever environmental damage to the delicate ecosystems such as coral reefs, seagrass beds, and beaches. At present, survey work is performed by hand – a method that is inefficient and difficult to perform reliably. Improved bottom survey tools are clearly needed to evaluate the extent and type of damage and assist in determining remediation efforts. ...

TECHNICAL ABSTRACT: NOAA and the National Weather Service maintain an immense network of automated maritime, surface, and upper-air observing stations throughout the world and at great expense. These automated stations provide regularly updated data for both short-term weather prediction and long-term climate models. Maritime and surface observations occur as frequently as every 10 to 20 minutes, ...

TECHNICAL ABSTRACT: The objective of this project is to research the technical feasibility of designing a software tool “Permit Wizard” that will automate the process for aquamarine permit application submittal, review, approval/disapproval and issue (including collection of fees). Aquaculture producers are currently faced with slow, complex, and often confusing permitting processes that must ...

TECHNICAL ABSTRACT: Creare proposes to develop a self-sustained small-scale power conversion system to power NOAA’s weather monitoring network stations located in harsh uninhabited locations. Our miniature heat engine will take advantage of the existing year-round thermal gradients found between water and air in Arctic regions. Our baseline approach is the development of a compact Turbo-Rankine ...

TECHNICAL ABSTRACT: We propose developing a new observational capability for measuring upper atmosphere (20-Km to 200-Km+ altitude) wind and temperature dynamics, based on Doppler imaging of Limb concentrations of NO, N2O, and CO2 called the Doppler Wind Temperature Sounder. The principle of operation is that by measuring the Doppler shift of trace gases created by the differential velocity betwee ...

Signature Research, Inc. (SGR) and Michigan Technological University (MTU) propose a Phase I STTR effort to develop a learning algorithm which exploits the spatio-spectral characteristics inherent within IR imagery and motion imagery.Our archive of modelled and labeled data sets will allow our team to thoroughly capture the variable elements that will drive machine learning performance.The overall ...

The objective of this project is to design a software architecture based on densely-connected neural network to perform automatic targetsegmentation and recognition using training datasets of limited size (low-shot). Deep learning architectures have proved to be extremelyeffective at object detection and recognition, but such capability comes at the cost of having large labeled datasets. Such data ...