The HyperLeaf2024 dataset contains 2410 hyperspectral images of wheat flag leaves. The goal is to develop methods for whole-image hyperspectral regression. All leaves and associated measurements are collected from the same field with varying plot parameters. There are 1590 training images taken from 24 plots and 820 test images from an additional 12 plots. The goal is to build models using the image data to predict the 8 targets.

Some tips:
*   The first 3 targets (GrainWeight, Gsw, PhiPS2) have a wide range of possible values and should be treated as a pure regression task.
*   There are only 3 possible values for the fertilizer content, 0.0, 0.5, 1.0. It may or may not be beneficial to treat this a classification task.
*   The last 4 targets (cultivars: Heerup, Kvium, Rembrandt, Sheriff) are one-hot encoded and thus for each sample, one of these has a value of 1.0 and the other three are 0.0. Therefore it may also be beneficial to treat this a classification task and include this restriction in your models.
*   Keep in mind the leaderboard metric is based on mean squared error, so rounding the targets to the nearest value (for fertilizer and cultivars) may reduce your score if the closest value is incorrect. 

## Files

*   **images** - folder containing all images in both train an test sets
*   **train.csv** - the training set, including the ImageId and the targets
*   **test.csv** - the test set, includes ImageId, targets hidden
*   **sample_submission.csv** - a sample submission file that simply predicts the mean values for each target

## Columns

*   `ImageId` - ID of the image, corresponds to filename in the images folder
*   `GrainWeight` - measurement of yield
*   `Gsw` - stomatal conductance
*   `PhiPS2` - chlorophyll fluorescence
*   `Fertilizer` - fertilizer level (0.0, 0.5, or 1.0)
*   `Heerup` - Heerup cultivar (0.0 or 1.0)
*   `Kvium` - Kvium cultivar (0.0 or 1.0)
*   `Rembrandt` - Rembrandt cultivar (0.0 or 1.0)
*   `Sheriff` - Sheriff cultivar (0.0 or 1.0)

## Wavelengths

These are the center wavelengths for each channel in the images:

    397.32, 400.20, 403.09, 405.97, 408.85, 411.74, 414.63, 417.52, 420.40, 423.29, 426.19, 429.08,
    431.97, 434.87, 437.76, 440.66, 443.56, 446.45, 449.35, 452.25, 455.16, 458.06, 460.96, 463.87,
    466.77, 469.68, 472.59, 475.50, 478.41, 481.32, 484.23, 487.14, 490.06, 492.97, 495.89, 498.80,
    501.72, 504.64, 507.56, 510.48, 513.40, 516.33, 519.25, 522.18, 525.10, 528.03, 530.96, 533.89,
    536.82, 539.75, 542.68, 545.62, 548.55, 551.49, 554.43, 557.36, 560.30, 563.24, 566.18, 569.12,
    572.07, 575.01, 577.96, 580.90, 583.85, 586.80, 589.75, 592.70, 595.65, 598.60, 601.55, 604.51,
    607.46, 610.42, 613.38, 616.34, 619.30, 622.26, 625.22, 628.18, 631.15, 634.11, 637.08, 640.04,
    643.01, 645.98, 648.95, 651.92, 654.89, 657.87, 660.84, 663.81, 666.79, 669.77, 672.75, 675.73,
    678.71, 681.69, 684.67, 687.65, 690.64, 693.62, 696.61, 699.60, 702.58, 705.57, 708.57, 711.56,
    714.55, 717.54, 720.54, 723.53, 726.53, 729.53, 732.53, 735.53, 738.53, 741.53, 744.53, 747.54,
    750.54, 753.55, 756.56, 759.56, 762.57, 765.58, 768.60, 771.61, 774.62, 777.64, 780.65, 783.67,
    786.68, 789.70, 792.72, 795.74, 798.77, 801.79, 804.81, 807.84, 810.86, 813.89, 816.92, 819.95,
    822.98, 826.01, 829.04, 832.07, 835.11, 838.14, 841.18, 844.22, 847.25, 850.29, 853.33, 856.37,
    859.42, 862.46, 865.50, 868.55, 871.60, 874.64, 877.69, 880.74, 883.79, 886.84, 889.90, 892.95,
    896.01, 899.06, 902.12, 905.18, 908.24, 911.30, 914.36, 917.42, 920.48, 923.55, 926.61, 929.68,
    932.74, 935.81, 938.88, 941.95, 945.02, 948.10, 951.17, 954.24, 957.32, 960.40, 963.47, 966.55,
    969.63, 972.71, 975.79, 978.88, 981.96, 985.05, 988.13, 991.22, 994.31, 997.40, 1000.49, 1003.58