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

Guardat en:
Dades bibliogràfiques
Publicat a:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences vol. X-G-2025 (2025), p. 503
Autor principal: Kumari, Priyanka
Altres autors: Soor, Sampriti, Shetty, Amba, Nair, Archana M
Publicat:
Copernicus GmbH
Matèries:
Accés en línia:Citation/Abstract
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3228951447
003 UK-CbPIL
022 |a 2194-9042 
022 |a 2194-9050 
024 7 |a 10.5194/isprs-annals-X-G-2025-503-2025  |2 doi 
035 |a 3228951447 
045 2 |b d20250101  |b d20251231 
084 |a 263032  |2 nlm 
100 1 |a Kumari, Priyanka  |u IPDF, Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, India; IPDF, Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, India 
245 1 |a A UNet Model for Accelerated Preprocessing of CRISM Hyperspectral Data for Mineral Identification on Mars 
260 |b Copernicus GmbH  |c 2025 
513 |a Journal Article 
520 3 |a 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 800 × 800 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. 
653 |a Preprocessing 
653 |a Spectra 
653 |a Mars 
653 |a Mars surface 
653 |a Mica 
653 |a Geological history 
653 |a Environmental 
700 1 |a Soor, Sampriti  |u IPDF, Center for Intelligent Cyber Physical Systems, Indian Institute of Technology Guwahati, Guwahati, India; IPDF, Center for Intelligent Cyber Physical Systems, Indian Institute of Technology Guwahati, Guwahati, India 
700 1 |a Shetty, Amba  |u Department of Water Resources and Ocean Engineering, National Institute of Technology Karnataka, Surathkal, India; Department of Water Resources and Ocean Engineering, National Institute of Technology Karnataka, Surathkal, India 
700 1 |a Nair, Archana M  |u Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, India; Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, India 
773 0 |t ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  |g vol. X-G-2025 (2025), p. 503 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3228951447/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3228951447/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch