A UNet Model for Accelerated Preprocessing of CRISM Hyperspectral Data for Mineral Identification on Mars

TL;DR

This paper introduces a UNet-based autoencoder for rapid spectral preprocessing of CRISM hyperspectral data, significantly reducing processing time while maintaining accuracy for Martian mineral identification.

Contribution

It presents a novel deep learning framework that automates and accelerates spectral preprocessing steps for hyperspectral data analysis on Mars.

Findings

Preprocessing time reduced from 1.5 hours to 5 minutes.

Achieves competitive accuracy in mineral classification.

Demonstrates effective spectral feature preservation.

Abstract

Accurate mineral identification on the Martian surface is critical for understanding the planet's geological history. This paper presents a UNet-based autoencoder model for efficient spectral preprocessing of CRISM MTRDR hyperspectral data, addressing the limitations of traditional methods that are computationally intensive and time-consuming. The proposed model automates key preprocessing steps, such as smoothing and continuum removal, while preserving essential mineral absorption features. Trained on augmented spectra from the MICA spectral library, the model introduces realistic variability to simulate MTRDR data conditions. By integrating this framework, preprocessing time for an 800x800 MTRDR scene is reduced from 1.5 hours to just 5 minutes on an NVIDIA T1600 GPU. The preprocessed spectra are subsequently classified using MICAnet, a deep learning model for Martian mineral identification. Evaluation on labeled CRISM TRDR data demonstrates that the proposed approach achieves competitive accuracy while significantly enhancing preprocessing efficiency. This work highlights the potential of the UNet-based preprocessing framework to improve the speed and reliability of mineral mapping on Mars.