{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# Precipitation in Germany\n",
    "\n",
    "![](images/rain.jpg) Image source: kulkann/Getty Images"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Task\n",
    "\n",
    "The goal of our second challenge is to estimate precipitation rates (in mm/h) in Germany based on Meteosat Second Generation (MSG) data."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "To this end, we provide the following preprocessed data sets from December 2017:\n",
    " - [MSG infrared bands (training)](https://hessenbox.uni-marburg.de/getlink/fiFQJDX1Aoqr43ERnnXu3gSE/MSG_201712.zip)\n",
    " - [MSG infrared bands (test)](https://hessenbox.uni-marburg.de/getlink/fiAyLJLuYdpqW9motETJaEYh/MSG_201712_test.zip)\n",
    " - [RADOLAN precipitation rates (target)](https://hessenbox.uni-marburg.de/getlink/fiQZ9Gku6t2zhuJg8XHU8JP3/Radolan_201712.zip)\n",
    "\n",
    "RADOLAN is a radar based product with precipitation rates in mm/h generated by the German Weather Service (DWD). You can find more information [here](https://www.dwd.de/DE/leistungen/radolan/radolan.html).\n",
    "\n",
    "MSG data are already clipped to Germany. RADOLAN data are reprojected to the same domain. \n",
    "The MSG data have a temporal resolution of 15 minutes. The Radolan data have a temporal resolution of 5 minutes and the units are mm/h.\n",
    "For the competition, the corresponding hourly scenes were compiled from both data sets.\n",
    "\n",
    "Below you find a visualization of both data sets for an exemplary time slot. Black areas around the domain boundaries are due to missing radar data in these regions.\n",
    "\n",
    "![](images/msg_rad_ex.png)\n",
    "\n",
    "RADOLAN data are provided for 595 training time slots. 149 additional RADOLAN scenes that were randomly selected are kept back for testing the submissions. The train/test split looks like this:\n",
    "\n",
    "![](images/train_test_distr.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Submission\n",
    "\n",
    "You should hand in the prediction results for all 149 test scenes (173x233 px) as **one** netcdf-file. As a guide, you can use this [template file](https://hessenbox.uni-marburg.de/getlink/fiVNBLbb5qB6hsH1NQiHD6Fb/submission_template.nc) and fill it with your predictions.\n",
    "\n",
    "Like the RADOLAN data used in training, your data should be submitted in units of mm/h. \n",
    "\n",
    "You can submit your results a maximum of 3 times. Only the best submission will be used for your ranking score.\n",
    "\n",
    "Results must be submitted via Ilias. Please also stick to the following file name format:\n",
    "\n",
    "    YYYY-mm-dd_version_alias.nc\n",
    "\n",
    "so for instance:\n",
    "\n",
    "    2021-12-01_V1_Catwoman.nc"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deadline\n",
    "\n",
    "January 30, 2022\n",
    "\n",
    "Results handed in after this deadline will not be rated."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Rating\n",
    "\n",
    "The rating will be based on the [R² score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html).\n",
    "\n",
    "It will be applied to all \"precipitating pixels\" in the 149 test scenes. This means that pixels which were not detected as precipitating (`0.0 mm/h`) by the radar network of the DWD will not be included in the scoring procedure."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Reward\n",
    "\n",
    "The first place will be rewarded with a 20€ \"Marburg Gutschein\".\n",
    "\n",
    "<img src=\"https://www.gutschein-marburg.de/file_data/template/assets/img/gutscheine_3.png\" alt=\"drawing\" width=\"400\"/>"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}