Connecting Meteorite Spectra to Lunar Surface Composition Using Hyperspectral Imaging and Machine Learning

Abstract

We present an innovative, cost-effective framework integrating laboratory Hyperspectral Imaging (HSI) of the Bechar010 Lunar meteorite with ground-based lunar HSI and supervised Machine Learning(ML) to generate high-fidelity mineralogical maps. A 3mm thin section of Bechar010 was imaged under a microscope with a 30mm focal length lens at 150mm working distance, using 6x binning to increase the signal-to-noise ratio, producing a data cube (X $\times$ Y $\times$ $λ$ = $791 \times 1024 \times 224$, 0.24mm $\times$ 0.2mm resolution) across 400-1000}nm (224 bands, 2.7nm spectral sampling, 5.5nm full width at half maximum spectral resolution) using a Specim FX10 camera. Ground-based lunar HSI was captured with a Celestron 8SE telescope (3km/pixel), yielded a data cube ($371 \times 1024 \times 224$). Solar calibration was performed using a Spectralon reference ({99}\% reflectance {<2}\% error) ensured accurate reflectance spectra. A Support Vector Machine (SVM) with a radial basis function kernel, trained on expert-labeled spectra, achieved {93.7}\% classification accuracy(5-fold cross-validation) for olivine ({92}\% precision, {90}\% recall) and pyroxene ({88}\% precision, {86}{\%} recall) in Bechar 010. LIME analysis identified key wavelengths (e.g., 485nm, {22.4}\% for M3; 715nm, {20.6}\% for M6) across 10 pre-selected regions (M1 to M10), indicating olivine-rich (Highland-like) and pyroxene-rich (Mare-like) compositions. SAM analysis revealed angles from 0.26 radian to 0.66 radian, linking M3 and M9 to Highlands and M6 and M10 to Mares. K-means clustering of Lunar data identified 10 mineralogical clusters ({88}\% accuracy), validated against Chandrayaan-1 Moon mineralogy Mapper ($\rm M^3$) data (140m/pixel, 10nm spectral resolution).A novel push-broom HSI approach with a telescope achieves 0.8 arcsec resolution for lunar spectroscopy, inspiring full-sky multi-object spectral mapping.

Figures (8)

• Figure S1: (Right): Experimental setup for HSI of Bechar 010 meteorite, featuring the Specim FX10 camera, halogen lamps, and motorized scanner covered 791 pixels. An example of the spectral data for the regions of interest (ROIs) is also provided, highlighted with colored lines. (Left): Celestron 8SE Nexstar telescope to create a hyperspectral image of the Moon via a scan using a custom push-broom spectrometer (400--1000 nm) technique to create the spectral image map. The HSI leveraged the Moon’s relative motion concerning Earth to perform the scan. The scan direction covered 371 pixels, which was sufficient to map the Lunar surface based on the Moon’s angular velocity (approximately 0.004°/s). An example of the spectral data for selected region is highlighted with the colored lines.
• Figure S2: Bechar 010 analysis: (Left:) Macroscopic RGB composite with regions (1--10) of interest marked (red triangles), (Right:) Median spectra from those ROIs compared with reference spectra of olivine and pyroxene.
• Figure S3: Box plot illustrating the distribution of probabilities across regions for meteorite regions classified by SVM based on Olivine and Pyroxene mixtures, as detailed in Table \ref{['tab:probabilities']}.
• Figure S4: Top five key spectral wavelengths influencing SVM classification decisions for Bechar 010, determined using LIME.
• Figure S5: Distribution of top five key wavelengths across meteorite regions M1--M10. Vertical dashed lines mark significant spectral features (labeled in nm), while y-axis values show their percentage importance within each region. Marker colors and labels indicate region membership (M1--M10), with the clustering at 480--525 nm and 650--760 nm reflecting dominant mineralogical signatures of olivine/pyroxene and high-Ca pyroxene, respectively. The extended features beyond 800 nm (particularly in M2, M5, M8--M9) suggest continuum influences from anorthite or secondary pyroxene phases.