Input data is provided in the form of two-dimensional files such that each row corresponds to a unique combination of latitude, longitude, year and crop. We provide separate files for each climate variable (precipitation, shortwave radiation, minimum and maximum daily temperature and mean daily temperature), which contain 240 columns reflecting daily values for 30 days before sowing and 210 days after. An additional file contains the dominant USDA soil texture class (constant over time), the ambient CO<sub>2</sub> concentration (spatially constant), the planting date and the nitrogen application rate (constant over time). Each input datapoint therefore consists of a multivariate time series of shape 5x240, plus several auxiliary variables. The target variable is a single value (end-of-season crop yield in tons per hectare) per unique gridcell, year and crop combination.

All the data is in .parquet format, and the predictive features have been split across several files due to their size to make it easier to work with. Each row corresponds to a unique datapoint (one growing season at one 0.5 degree grid cell), with columns corresponding to different variables, and the column ID as a unique identifier.

The training set consists of the first 39 years, covering 1982 to 2020; this can be used for training your models. The resulting yields are provided in the files `train_solutions_maize.parquet` and `train_solutions_wheat.parquet`.

The test set is twice as big as the training set, covering the 78 years from 2021 to 2098. The first 30 of those years (2021-2050) will be used to measure your models' performance (using RMSE as scoring metric) on the public leaderboard during the challenge, and model performance on the rest of the years will be revealed after the challenge ends.

## Files

* Training data (1982-2020)
    - For each crop (maize and wheat)
        - Five files containing climate variables from 30 days before and 210 days after planting date
            + rsds - daily short-wave radiation
            + pr - daily precipitation
            + tas - daily mean temperature
            + tmax - daily maximum temperature
            + tmin - daily minimum temperature
        - One “solutions” file containing the target variable (yield)
    - Soil
        - One file containing soil texture, real year, nitrogen fertilization rate and CO<sub>2</sub> concentration
* Test data (2021-2098)
    - For each crop (maize and wheat)
        - Five files containing climate variables from 30 days before and 210 days after planting date
            + rsds - daily short-wave radiation
            + pr - daily precipitation
            + tas - daily mean temperature
            + tmax - daily maximum temperature
            + tmin - daily minimum temperature
    - Soil
        - One file containing soil texture, real year, nitrogen fertilization rate and CO<sub>2</sub> concentration
* sample_submission.csv - an example of how your submitted predictions file should look.

**Important note:** To make it easier for participants to work with, we have split most of the data files between the two crops (maize and wheat). However, submission files should include predictions for **both** crops.

## Columns

All files contain an `ID` column, which is a unique ID for each datapoint (crop, gridcell and year). Apart from **train_crop_solutions.csv**, all other files also contain columns `lat`, `lon`, `year` and `crop`. Note that `year` is **not** the 'real year' but reflects the number of growing seasons since the start of the simulation run. However, the 'real year' can be found in the **soil_co2_*.parquet** files in the column `real_year`. In these files, `texture_class` contains the dominant USDA soil texture class (categorical variable coded as 1 to 13) and `co2` contains the ambient CO<sub>2</sub> concentration in parts per million. Finally, `nitrogen` describes the annual fertilization rate in tons per hectare per growing season.

Additional units: short-wave radiation [W m<sup>-2</sup>], precipitation [kg m<sup>-2</sup> s<sup>-1</sup>], temperatures [<sup>o</sup> C], yield [t ha<sup>-1</sup>]].

Because the dataset is very large, each climate variable is in a separate file to make it easier to work with - you might not want to use all of the variables at first. Each file contains 240 columns reflecting one daily value, from 30 days before sowing until 210 days after, as well as a column called `variable` with the name of the variable being measured (e.g. pr, tas or rsds), and columns describing the year, latitude, longitude and crop, as well as the unique `ID` to facilitate joining the datasets.