SpectroscopyNet: Learning to pre-process Spectroscopy Signals without clean data
This addresses the challenge of noise removal in spectroscopy for applications like planetary science, though it is incremental as it builds on existing deep learning techniques.
The authors tackled the problem of cleaning spectroscopy signals from instrument noise without needing clean data, achieving superior performance compared to standard feature-engineered methods on a LIBS dataset from the ChemCam instrument.
In this work we propose a deep learning approach to clean spectroscopy signals using only uncleaned data. Cleaning signals from spectroscopy instrument noise is challenging as noise exhibits an unknown, non-zero mean, multivariate distributions. Our framework is a siamese neural net that learns identifiable disentanglement of the signal and noise components under a stationarity assumption. The disentangled representations satisfy reconstruction fidelity, reduce consistencies with measurements of unrelated targets and imposes relaxed-orthogonality constraints between the signal and noise representations. Evaluations on a laser induced breakdown spectroscopy (LIBS) dataset from the ChemCam instrument onboard the Martian Curiosity rover show a superior performance in cleaning LIBS measurements compared to the standard feature engineered approaches being used by the ChemCam team.