# Beyond Visible Spectrum: AI for Agriculture 2024 — Data

来源：https://www.kaggle.com/competitions/beyond-visible-spectrum-ai-for-agriculture-2024/data

采集时间：2026-10-19T07:23:55Z

The hyperspectral imagery retrieval was carried out in two times, on 3 May and 8 May 2019. On 3 May 2019 wheat in the experimental area was in the pre-grouting stage, which is a critical period for the spread of downy mildew infestation. On 8 May 2019 wheat in the experimental area was in the middle of the grouting stage, which is the period when the symptoms of downy mildew are more obvious.

A DJI M600 Pro 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 S185 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.  Since UAV hyperspectral data are interfered by noise in post-processing, which has a significant impact on the data at both ends of the bands, the first 10 bands as well as the last 14 bands were excluded from the study, leaving 100 bands. In this work, all the images were obtained at an altitude of 60 meters, with a spatial resolution close to 4cm 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)


## Files

The training dataset
The validation dataset

##Submission Columns

*   `Id` - file name
*   `Category` - 1: Mild FHB 2:  Serious FHB