MULTI-MODAL global surveillance methodology for predictive and on-demand characterization of localized processes using cube satellite platforms and deep learning techniques
This paper presents the work completed towards the development of a multi-modal global surveillance methodology using cube satellite (CubeSat) platforms and novel data analysis techniques. A CubeSat system equipped with adequate sensors and data analytics capabilities can autonomously characterize various phenomena of interest on the Earth’s surface. CubeSats are advantageous over conventional satellites in certain remote monitoring applications because of their reduced construction costs (due to the availability of commercially-off-the-shelf components) and are easier to launch. The CubeSat surveillance system developed in this paper focused on phenomena of interest surrounding the nuclear fuel cycle in support of nuclear non-proliferation and emergency response. To observe the phenomena, a constellation of 3U and 6U CubeSats deployed from the ISS with adequate components was chosen. Four different sensor configurations were identified for remote sensing: panchromatic/multispectral in the visible and near-infrared spectrum, multispectral in infrared spectrum, hyperspectral in infrared spectrum, and multispectral in ultraviolet spectrum. While a panchromatic/multispectral sensor configuration has CubeSat flight heritage at the required spatial resolutions, the other three sensor types need future 3 development to meet signature and system requirements. Once each sensor onboard the CubeSat system collects data on a target of interest, the onboard computers would then apply the deep learning-based characterization methodology developed in this paper to identify phenomena. Four surrogate datasets containing representative simplified “images” were created for each sensor type to train the characterization methodology. A convolutional neural network was applied to each dataset and produced recall rates for the phenomena between 89.7% - 99.3% and precision rates between 92.3% - 99.9%. Each phenomenon’s presence probability from each network is then combined into a final characterization solution for a target area. This paper covers multiple interdisciplinary areas to develop the foundation for a CubeSat surveillance system focused on phenomena surrounding the nuclear fuel cycle.
- Research Organization:
- Georgia Tech Research Corporation, Atlanta, GA (United States). Institute of Technology
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- NA0003921
- OSTI ID:
- 1780573
- Alternate ID(s):
- OSTI ID: 1782896
- Journal Information:
- Remote Sensing Applications: Society and Environment, Vol. 22; ISSN 2352-9385
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Relative radiometric correction of QuickBird imagery using the side-slither technique on-orbit.
Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS