Generation and performance of automated jarosite mineral detectors for visible/near-infrared spectrometers at Mars

Gilmore, M. S.; Bornstein, B.; Merrill, Matthew D.; Castaño, Rebecca; Greenwood, J. P.

doi:10.1016/j.icarus.2007.11.025

Cited by 9 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, discriminant analysis was used to identify additives in honey using Fourier Transform-Raman spectroscopy. [14] Support vector machines have been used broadly, with applications including mineral detection with near-infrared spectroscopy [15] and composition prediction with Raman spectra. [16] Artificial neural networks (ANNs) have seen increasing use in spectroscopic applications as well.…”

Section: Introductionmentioning

confidence: 99%

“…[17][18][19] Similarity-based methods for both peak-feature [6] and full-spectrum matching [20,21] have also been explored, especially for Raman spectroscopy. Some approaches restrict the task to identification of a specific component, [14,15] while others attempt to cluster spectra into logical groups. [19,22] Most methods employ some combination of spectrum preprocessing steps to reduce the influence of noise and fluorescence, [23,24] and some also project spectra into a lower-dimensional feature space, typically using principal components analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning tools formineral recognition and classification from Raman spectroscopy

Carey

Boucher

Mahadevan

et al. 2015

J Raman Spectroscopy

View full text Add to dashboard Cite

Tools for mineral identification based on Raman spectroscopy fall into two groups: those that are largely based on fits to diagnostic peaks associated with specific phases, and those that use the entire spectral range for multivariate analyses. In this project, we apply machine learning techniques to improve mineral identification using the latter group. We test the effects of common spectrum preprocessing steps, such as intensity normalization, smoothing, and squashing, and found that the last is superior. Next, we demonstrate that full-spectrum matching algorithms exhibit excellent performance in classification tasks, without requiring time-intensive dimensionality reduction or model training. This class of algorithms supports both vector and trajectory input formats, exploiting all available spectral information. By combining these insights, we find that optimal mineral spectrum matching performance can be achieved using careful preprocessing and a weighted-neighbors classifier based on a vector similarity metric. IntroductionUse of Raman spectroscopy in the geosciences is growing rapidly, as evidenced by burgeoning publications in the fields of geology, cultural anthropology, environmental science, and, in particular, planetary science. Raman spectrometers have been proposed for exploration of a diverse range of extraterrestrial targets including asteroids, [1] Europa, [2,3] Mars, [4][5][6] the Moon, [7] and Venus. [8] A Raman laser spectrometer (RLS) is part of the science instrument payload of the European Space Agency 2018 ExoMars mission; the RLS instrument will target mineralogical and astrobiological investigations on the surface and subsurface of Mars. [9,10] Raman will also be used on the upcoming NASA Mars 2020 mission as part of the SuperCam and SHERLOC instruments. [11] What all these applications have in common is their dependence on software and mineralogical databases for phase identification and quantification of relative abundances of mineral components. Because of the structural diversity and chemical complexity of naturally occurring minerals, optimal applications for these purposes require an infusion of work into development of appropriate software and mineral databases.In practice, users commonly depend on a combination of matching software distributed by spectrometer manufacturers and one-on-one comparisons with database spectra for their identifications, but these types of identification have two critical limitations. First, identifications are only as good as the databases used to match them. No database can be entirely comprehensive, so it cannot be unequivocally claimed that any spectrum is a 'perfect match' to exactly one other phase.The RRUFF database was founded in 2006 at Arizona State University by Robert Downs to remedy this situation by providing coverage of all known mineral species. [12] It has quickly become the preeminent resource available for Raman spectra of minerals. RRUFF currently contains over 20 378 spectra acquired at several different laser wavelengths from orien...

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning tools formineral recognition and classification from Raman spectroscopy

Carey

Boucher

Mahadevan

et al. 2015

J Raman Spectroscopy

View full text Add to dashboard Cite

show abstract

“…The lack of spatial information in single spectrum observations suggests that these should be reserved for specific observations on identified targets, rather than employed in a “blind” manner. These results might also have implications for autonomous spectral fitting algorithms [e.g., Gilmore et al , 2007] designed to identify and examine targets of interest in spectral data without scientist intervention.…”

Section: Implications For Marsmentioning

confidence: 97%

Surface and subsurface composition of the Life in the Atacama field sites from rover data and orbital image analysis

et al. 2007

View full text Add to dashboard Cite

[1] The Life in the Atacama project examined six different sites in the Atacama Desert (Chile) over 3 years in an attempt to remotely detect the presence of life with a rover. The remote science team, using only orbital and rover data sets, identified areas with a high potential for life as targets for further inspection by the rover. Orbital data in the visible/near infrared (VNIR) and in the thermal infrared (TIR) were used to examine the mineralogy, geomorphology, and chlorophyll potential of the field sites. Field instruments included two spectrometers (VNIR reflectance and TIR emission) and a neutron detector: this project represents the first time a neutron detector has been used as part of a ''science-blind'' rover field test. Rover-based spectroscopy was used to identify the composition of small scale features not visible in the orbital images and to improve interpretations of those data sets. The orbital and ground-based data sets produced consistent results, suggesting that much of the field sites consist of altered volcanic terrains with later deposits of sulfates, quartz, and iron oxides. At one location (Site A), the ground-based spectral data revealed considerably greater compositional diversity than was seen from the orbital view. One neutron detector transect provided insight into subsurface hydrogen concentrations, which correlated with life and surface features. The results presented here have implications for targeting strategies, especially for future Mars rover missions looking for potential habitats/paleohabitats. , et al. (2007), Surface and subsurface composition of the Life in the Atacama field sites from rover data and orbital image analysis,

show abstract

An automated mineral classifier using Raman spectra

Ishikawa

Gulick

2013

Computers & Geosciences

View full text Add to dashboard Cite

Generation and performance of automated jarosite mineral detectors for visible/near-infrared spectrometers at Mars

Cited by 9 publications

References 45 publications

Machine learning tools formineral recognition and classification from Raman spectroscopy

Machine learning tools formineral recognition and classification from Raman spectroscopy

Surface and subsurface composition of the Life in the Atacama field sites from rover data and orbital image analysis

An automated mineral classifier using Raman spectra

Contact Info

Product

Resources

About