Our dataset consists of 2410 hyperspectral images of wheat flag leaves recorded with the portable SpecimIQ (Oulu, Finland) hyperspectral camera. Each image contains a single leaf and has dimensions of 48 x 352 and covers 204 spectral channels in the 400nm-1000nm range. The result is a data cube of shape 48 x 352 x 204. 

For each image there are 4 regression targets: yield (GrainWeight), stomatal conductance (Gsw), chlorophyll fluorescence (PhiPS2), and fertilizer. Additionally, we include a cultivar classification task that has been one-hot encoded (Heerup, Kvium, Rembrandt, Sheriff) and converted into a regression task to facilitate Kaggle's single metric leaderboard. The challenge goal is to develop methods that can be used to predict theses 5 targets as accurately as possible. 

Globally, wheat is one of the main sources of food. Its continued and effective yield in an increasingly harsh climate is essential to providing the nutrients we need in the years to come. As a result, developing methods to research and analyze crops is an important step towards producing effective treatments and mitigating the negative effects of climate change on the global food supply. Hyperspectral imaging is a commonly used technique in the agriculture research to monitor the growth and health of plants. Hyperspectral imaging records both the spatial information, as in a typical RGB image, as well as the spectral information. It works by recording a spectral reflectance curve for each pixel, in turn producing an image with a channel for each wavelength that the camera records. The result is a hyperspectral data cube with two spatial dimensions and one spectral.