# Beyond Visible Spectrum: AI for Agriculture 2023 — Data

来源：https://www.kaggle.com/competitions/beyond-visible-spectrum-ai-for-agriculture-P1/data

采集时间：2026-10-19T07:43:12Z

The hyperspectral imagery retrieval was conducted five times from the 25th, April to the 18th, May in 2018 to cover the entire growing season of winter wheat. A DJI S1000 UAV system (SZ DJI Technology Co Ltd., Gungdong, China) with a snapshot hyperspectral sensor was used for data acquisition. The model of the hyperspectral sensor was UHD 185 Firefly (UHD 185) which can obtain reflect radiation from the visible to near-infrared band between 450-950nm wavelength. The spectral resolution was 4nm. The raw data was recorded as a 1000*1000 panchromatic image and a 50*50 hyperspectral image with 125 bands. With a data fusion processed by the Cubert software, the output was a 1000*1000 image with 125bands, and the image was also mosaiced and orthorectified. In this work, all the images were obtained at an altitude of 30 meters, with a spatial resolution close to 2cm per pixel. 

# Dataset Overview Paper 
[A Deep Learning-Based Approach for Automated Yellow Rust Disease Detection from High-Resolution Hyperspectral UAV Images](https://www.mdpi.com/2072-4292/11/13/1554)
![](assets/084007538a2c81e0e09fc26a.png)


## Files

The training dataset
The validation dataset

##Submission Columns

*   `Id` - file name
*   `Category` - Rust, Health, Other