Denoising aerial gamma-ray surveying through non-linear dimensionality reduction



This paper addresses the problem of denoising aerial gamma-ray surveying in mining exploration. Conventional methods for denoising spectral data make strong assumptions about the levels and type of noise which reduces their efficiency. The proposed methodology cast the problem as manifold learning followed by non-linear regression. The model makes no assumptions about the level and type of noise and performs significantly better than previous techniques on both synthetic and real data. © 2007 Wiley Periodicals, Inc.