AVIRIS-NG-like smart virtual remote sensing via spectra-aware physics informed GANs
Data files
Nov 26, 2025 version files 543.19 MB
-
aviris-ng.zip
543.18 MB
-
README.md
1.60 KB
Abstract
This paper aims to create a physics informed virtual replica of the hyperspectral image captured by NASA’s Airborne Visible InfraRed Imaging Spectrometer - Next Generation (AVIRIS-NG) sensor equipped on manned aircraft. Few image samples are selected from study site around New Mexico, USA from flight mission ran in 2019. Out of 425 bands, 8 bands are utilized. For each band, reflectance spectra are chosen from United States Geological Survey (USGS) based on site specific geographical features. These spectras are infused during the image generation process with the correction check using matched filters. Moreover, we include the methane plumes along with other closely related hydrocarbons during the image generation process. Generative Adversarial Networks (GANs) architecture is employed with physics informed loss function for generating realistic and physically plausible images. Additionally, we also propose a new light weight dataset for creating the virtual replica of the AVIRIS-NG sensor on selected 8 bands in the visible light spectrum and the short-wave infrared region.
Dataset DOI: 10.5061/dryad.msbcc2gbt
Description of the data and file structure
aviris-ng.zip: This is light weight 8 channel benchmark dataset for synthesis of hyperspectral image from NASA JPL , AVIRIS-NG sensor. The dataset consist of 3 channels from visible spectrum (RGB- 460 nm, 550 nm, 640 nm) and 5 channels (2004 nm, 2109 nm, 2310 nm, 2350 nm, 2360 nm) in Short wave Infrared(SWIR) spectrum from paper title "AVIRIS-NG-like smart virtual remote sensing via spectra-aware physics informed GANS".
"Train" and "test" directories consist of train and test data. Both of these directories have "Hyper" folder which contains the 5 channel SWIR in .tif format. Also, both train and test folders have "Multi" directory contains 3 channel RGB in .tif format.
BibTeX for paper:
@inproceedings{giri2025aviris, title={AVIRIS-NG-Like Smart Virtual Remote Sensing via Spectra-Aware Physics Informed GANs}, author={Giri, Sachin and Krzysiak, Rafal and Hollenbeck, Derek and Chen, YangQuan}, booktitle={International Design Engineering Technical Conferences and Computers and Information in Engineering Conference}, volume={89251}, pages={V005T07A001}, year={2025}, organization={American Society of Mechanical Engineers} }
CC/More details - https://avirisng.jpl.nasa.gov/
Code/software
Contact at sachingiri@ucmerced.edu if you need full code for the paper