datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MARS-Hyperspectral-EnMAP-PRISMA-v2025
MARS-Hyperspectral dataset (EnMAP and PRISMA) - version v2025
Updated version of the dataset. More information will be added soon.
hyperspectral-orchard
Living Optics Orchard Dataset
Overview
This dataset contains 435 images of captured in one of the UK's largest orchards, using the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
The dataset is derived from 44 unique raw files corresponding to 435 frames.
Therefore, multiple frames could originate from the same raw file.
This structure emphasized the need for a split strategy that avoided data leakage.
To… See the full description on the dataset page: https://huggingface.co/datasets/LivingOptics/hyperspectral-orchard.MARS-Hyperspectral
MARS-Hyperspectral dataset
This repository contains the data for the work publicly presented at:
[ArXiv preprint] Růžička, Mateo-García, Irakulis-Loitxate et al., Operational machine learning for remote spectroscopic detection of CH4 point sources, arXiv preprint arXiv:2511.07719 (2025).
[Poster] Růžička, Mateo-García, Irakulis-Loitxate et al., Machine Learning Models for Multi-sensor Detection of Methane Leaks in Hyperspectral Data, June. 23-27, 2025, ESA Living Planet Symposium… See the full description on the dataset page: https://huggingface.co/datasets/UNEP-IMEO/MARS-Hyperspectral.Hyperspectral_Image_Datasetkaist-hyperspectral
Description
The exr folder contains a high-resolution dataset, consisting of 30 hyperspectral images covering a wide spectral range.The acquisitions have 31 channels in the range 420-720 nm, with a separation of 10 nm.
The spectral images are reflectance images, which are normalized by the intensity of the reference white of Spectralon (calibrated 99% reflectance).
Capture setup
Camera: Pointgrey Grasshopper 9.1MP Monochromatic (GS3-U3-91S6M-C)
Lens: Jenoptik UV-VIS-IR… See the full description on the dataset page: https://huggingface.co/datasets/danaroth/kaist-hyperspectral.hyperspectral-fruit
Living Optics Hyperspectral Fruit Dataset
Overview
This dataset contains 100 images of various fruits and vegetables captured under controlled lighting, with the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
From the 100 images, we extract >430,000 spectral samples, of which >85,000 belong to one of the 19 classes in the dataset. The rest of the spectra can be used for negative sampling when training… See the full description on the dataset page: https://huggingface.co/datasets/LivingOptics/hyperspectral-fruit.Hyperspectral-Polarimetric-BRDFsalmonella-serovar-hyperspectral
Salmonella Serovar Hyperspectral Microscopy (Foods 2025)
Salmonella Serovar Hyperspectral Microscopy is an image dataset for foodborne bacterial classification using hyperspectral imaging. It was created to support research in rapid pathogen identification, enabling models to classify Salmonella serovars directly from microscopy images without the need for selective enrichment.
Companion spectral dataset: The single-cell spectral features (tabular, 25,972 rows) extracted from these… See the full description on the dataset page: https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral.HyperspectralTinyMARS-Hyperspectral-EMIT-v2025
MARS-Hyperspectral dataset (EMIT) - version v2025
Updated version of the dataset. More information will be added soon.
hyperspectral-fruit
Living Optics Hyperspectral Fruit Dataset
Overview
This dataset contains 100 images of various fruits and vegetables captured under controlled lighting, with the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
From the 100 images, we extract >430,000 spectral samples, of which >85,000 belong to one of the 19 classes in the dataset. The rest of the spectra can be used for negative sampling when… See the full description on the dataset page: https://huggingface.co/datasets/duc08042006/hyperspectral-fruit.hyperspectral-sim-s2-waters-taco
Hyperspectral simulations for Sentinel-2 waters
266,471 simulated water-leaving remote sensing reflectance spectra with the inherent optical properties that generated them. Forward-modelled with the Bi et al. (2023) bio-geo-optical model through the WaterQuality framework (Koenig et al. 2023) and convolved to eight Sentinel-2 MSI bands (B1-B7, B8A).
266,471 samples · splits: test 26,647 · train 213,177 · validation 26,647 · tasks: regression
Packaged as… See the full description on the dataset page: https://huggingface.co/datasets/isp-uv-es/hyperspectral-sim-s2-waters-taco.hyperspectral_reconstruction_datasets
Robust hyperspectral reconstruction from satellite and airborne observations via a deep hierarchical fusion network across heterogeneous scenarios
Fujiang Ji a, Jiaqi Yang a, Philip A. Townsend a, Ting Zheng a, Kyle R. Kovach a, Tong Yu b, Ruqi Yang a, Ming Liu c, Min Chen a
a Department of Forest and Wildlife Ecology, University of Wisconsin-Madison, Madison, WI, USAb Department of Biological Systems Engineering, University of Wisconsin-Madison, Madison, WI, USAc Department of Computer… See the full description on the dataset page: https://huggingface.co/datasets/FujiangJi/hyperspectral_reconstruction_datasets.salmonella-serovar-hyperspectral-spectra
Salmonella Serovar Hyperspectral Spectra (Foods 2025)
Salmonella Serovar Hyperspectral Spectra is a tabular dataset of single-cell spectral features for foodborne bacterial classification. It was created to support research in rapid pathogen identification, enabling models to classify Salmonella serovars using hyperspectral signatures extracted from individual bacterial cells.
Companion image dataset: The RGB composite microscopy images from which these spectra were extracted are… See the full description on the dataset page: https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral-spectra.HyperspectralCollections
Hyperspectral Image Collections
Collect the open-source hyperspectral images and train any deep models.
hyperspectral-plant-virus
Super Beet Virus Classification Dataset
Access the Data
You can access this dataset via the Living Optics Cloud Portal.
Motivation
Enhancing Sugar Beet Health Monitoring
Sugar beet crops are susceptible to various viral infections that can significantly impact yield and quality. Early and accurate detection of these viruses is crucial for effective disease management and crop protection.
Leveraging Hyperspectral Imaging for Disease… See the full description on the dataset page: https://huggingface.co/datasets/LivingOptics/hyperspectral-plant-virus.plant-disease-detection-hyperspectral-imaginghyperspectral-fruit
Living Optics Hyperspectral Fruit Dataset
Overview
This dataset contains 100 images of various fruits and vegetables captured under controlled lighting, with the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
From the 100 images, we extract >430,000 spectral samples, of which >85,000 belong to one of the 19 classes in the dataset. The rest of the spectra can be used for negative sampling when… See the full description on the dataset page: https://huggingface.co/datasets/fix666/hyperspectral-fruit.hyperspectral-grapes
Non-contact sugar estimation with hyperpsectral data
Access the data
You can now access this dataset via the Living Optics Cloud Portal
Motivation
Precision viticulture and adaptive harvesting
Wine quality is heavily dependent on the grape maturity at harvest and can decline by 10% in a week. To maximise quality, the harvest time of grape berries should be optimised for
sugar levels, usually measured as total soluble solids (TSS) or Brix
berry… See the full description on the dataset page: https://huggingface.co/datasets/LivingOptics/hyperspectral-grapes.precision_agriculture_drone_hyperspectralMARS-Hyperspectral-EMIT-mini
MARS-Hyperspectral-EMIT-mini
"Mini" version of the full dataset released at https://huggingface.co/datasets/UNEP-IMEO/MARS-Hyperspectral - this one contains only 9 of our 256x256 tiles and a csv linking these. It can be used in code demos for easy-to-setup demonstration of training runs (but naturally the models won't really work - for that they need to be trained on the full data).
Mini dataset is uploaded on this account to lower the congestion on the main UNEP-IMEO page.
For any… See the full description on the dataset page: https://huggingface.co/datasets/previtus/MARS-Hyperspectral-EMIT-mini.hyperspectral-orchard
Living Optics Orchard Dataset
Overview
This dataset contains 435 images of captured in one of the UK's largest orchards, using the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
The dataset is derived from 44 unique raw files corresponding to 435 frames.
Therefore, multiple frames could originate from the same raw file.
This structure emphasized the need for a split strategy that avoided data leakage.
To… See the full description on the dataset page: https://huggingface.co/datasets/hkursat/hyperspectral-orchard.hyperspectral-dynamic-streamHyperspectralGrapevineVarieties
Original archival record
This Hugging Face repository mirrors the dataset archived on Zenodo.
DOI: 10.5281/zenodo.15834062
Brief overview
This dataset accompanies the journal article "Classification of Grapevine Varieties Using UAV Hyperspectral Imaging," published in Remote Sensing (MDPI): https://doi.org/10.3390/rs16122103.
It contains hyperspectral images acquired by an unmanned aerial vehicle (UAV) covering seventeen grapevine varieties, grouped into… See the full description on the dataset page: https://huggingface.co/datasets/allopezr/HyperspectralGrapevineVarieties.hyperspectral-fruit
Living Optics Hyperspectral Fruit Dataset
Overview
This dataset contains 100 images of various fruits and vegetables captured under controlled lighting, with the Living Optics Camera.
The data consists of RGB images, sparse spectral samples and instance segmentation masks.
From the 100 images, we extract >430,000 spectral samples, of which >85,000 belong to one of the 19 classes in the dataset. The rest of the spectra can be used for negative sampling when training… See the full description on the dataset page: https://huggingface.co/datasets/inihsor/hyperspectral-fruit.Chinese-Orbita-hyperspectral-satellites