Abstract
We consider fusion of heterogeneous data, consisting of multispectral imagery collected from the WorldView-2 satellite and aerial gamma-ray spectra collected during the NNSA Aerial Measuring System response to the Fukushima Dai-ichi Nuclear Power Plant crisis. These data are analyzed using the non-linear dimension reduction technique of diffusion maps. The data is then used for classification of regions in the scene. A strong spatial coherence is observed in the gamma-ray data that is closely coupled to the underlying terrain classification obtained from the multispectral data, indicating correlation between these a priori uncorrelated measurements.
Similar content being viewed by others
References
Coifman RR, Lafon S, Lee A, Maggioni M, Nadler B, Warner F, Zucker S (2005) Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. Proc Natl Acad Sci 102:7426–7431
Lafon S, Keller Y, Coifman RR (2006) Data fusion and multicue data matching by diffusion maps. IEEE T Pattern Anal 28:1784–1797
Benedetto JJ, Cloninger A, Czaja W, Doster T, Kochersberger K, Manning B, McCullough T, McLean M (2014) Operator-based integration of information in multimodal radiological search mission with applications to anomaly detection. Proc SPIE 9073:90731A
Smith PEJ, Milton O, Adams JB (1986) Quantitative determination of mineral types and abundances from reflectance spectra using principal components analysis. J Geophys Res 90:C797–C804
Ramos F, Dickson B, Kumar S (2007) Denoising aerial gamma-ray surveying through non-linear dimensionality reduction. J Field Robot 24:849–861
Jones AE, Turner P, Zimmerman CH, Goulermas JY (2014) Classification of spent reactor fuel for nuclear forensics. Anal Chem 86:5399–5405
Heydon A, Cooper C, Thompson P, Turner PG, Gregg R, Hesketh K, Goulermas JY, Jones AE (2014) The UK’s contribution to the galaxy serpent table top exercise. J Nucl Mat 42:55–64
Bachmann CM, Ainsworth TL, Fusina RA (2005) Exploiting manifold geometry in hyperspectral imagery. IEEE T Geosci Remote 43:441–454
Sun W, Halevy A, Benedetto JJ, Czaja W, Liu C, Wu H, Shi B, Li W (2014) UL-Isomap based nonlinear dimensionality reduction for hyperspectral imagery classification. ISPRS J Photogramm 89:25–36
Sun W, Halevy A, Benedetto JJ, Czaja W, Li W, Liu C, Shi B, Wang R (2014) Nonlinear dimensionality reduction via the enh-ltsa method for hyperspectral image classification. IEEE J Sel Top App 7:375–388
Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 1396:1373–1396
Czaja W, Ehler M (2013) Schroedinger eigenmaps for the analysis of bio-medical data. IEEE T Pattern Anal 35:1274–1280
van der Maaten LJP, Postma EO, van den Herik HJ (2009) Dimensionality reduction: a comparative review. Tilburg University Technical Report TiCC-TR 2009-005
van der Maaten LJP, Hinton GE (2008) Visualizing High-Dimensional Data Using t-SNE. J Mach Learn Res 9:2579–2605
Cloninger A, Czaja W, Doster T (2014) Operator analysis and diffusion based embeddings for heterogeneous data fusion. Int Geosci Remote Se 2014:1249–1252
Acknowledgments
This work was supported in part by a research grant From the Defense Threat Reduction Agency, Basic Science for Combatting Weapons of Mass Destruction, HDTRA1-13-1-0015 “Harmonic Analysis Methods for Autonomous Radiological Search: A Data Driven Approach”. The authors gratefully acknowledge Chae Clark and Dan Weinberg from the University of Maryland for valuable insights into the computational techniques used in the data analysis.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Czaja, W., Manning, B., McLean, L. et al. Fusion of aerial gamma-ray survey and remote sensing data for a deeper understanding of radionuclide fate after radiological incidents: examples from the Fukushima Dai-Ichi response. J Radioanal Nucl Chem 307, 2397–2401 (2016). https://doi.org/10.1007/s10967-015-4650-z
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10967-015-4650-z