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

We have developed two automated detectors that can recognize the sulfate mineral jarosite in unknown visible to near-infrared spectra (350–2500 nm). The two detectors are optimized for use within the terrestrial and martian atmospheres. The detectors are built from Support Vector Machines trained using a generative model to create linear mixtures of library mineral spectra. Both detectors performed with an average ∼90% accuracy on laboratory spectra of single minerals and the laboratory and field spectra of rocks collected in a hydrothermal environment. This type of algorithm will contribute to the efficiency of onboard data analysis of landed and orbital visible/near-infrared spectrometers at Mars.