A UNet Model for Accelerated Preprocessing of CRISM Hyperspectral Data for Mineral Identification on Mars
Guardat en:
| Publicat a: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences vol. X-G-2025 (2025), p. 503 |
|---|---|
| Autor principal: | |
| Altres autors: | , , |
| Publicat: |
Copernicus GmbH
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full Text - PDF |
| Etiquetes: |
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 |