geetools_VH/example_jupyter.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# *CoastSat*: example at Narrabeen-Collaroy, Australia\n",
    "\n",
    "This software is described in *Vos K., Splinter K.D., Harley M.D., Simmons J.A., Turner I.L. (submitted). CoastSat: a Google Earth Engine-enabled software to extract shorelines from publicly available satellite imagery, Environmental Modelling and Software*. It enables the users to extract time-series of shoreline change over the last 30+ years at their site of interest.\n",
    "\n",
    "There are two main steps:\n",
    "- retrieval of the satellite images of the region of interest from Google Earth Engine\n",
    "- extraction of the shorelines from the images using a sub-pixel resolution technique\n",
    "\n",
    "## 1. Initial settings\n",
    "\n",
    "Refer to the **Installation** section of the README for instructions on how to install the Python packages necessary to run the software, including Google Earth Engine Python API. If that step has been completed correctly, the following packages should be imported without any problem."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pickle\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "import matplotlib.pyplot as plt\n",
    "import SDS_download, SDS_preprocess, SDS_shoreline, SDS_tools"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Retrieval of the images from GEE\n",
    "\n",
    "Define the region of interest (`polygon`), the date range (`dates`) and the satellite missions (`sat_list`) from which you wish to retrieve the satellite images. The images will be cropped on the Google Earth Engine server and only the region of interest will be downloaded as a .TIF file. The files will be organised in the local directory under *.\\data\\sitename*."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# region of interest (longitude, latitude)\n",
    "polygon = [[[151.2957545, -33.7012561],\n",
    "            [151.297557, -33.7388075],\n",
    "            [151.312234, -33.7390216],\n",
    "            [151.311204, -33.701399],\n",
    "            [151.2957545, -33.7012561]]]   \n",
    "# date range\n",
    "dates = ['2017-12-01', '2018-01-01']\n",
    "# satellite missions\n",
    "sat_list = ['S2']\n",
    "# name of the site\n",
    "sitename = 'NARRA'\n",
    "# put all the inputs into a dictionnary\n",
    "inputs = {'polygon': polygon, 'dates': dates, 'sat_list': sat_list, 'sitename': sitename}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Retrieve satellite images from GEE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metadata = SDS_download.retrieve_images(inputs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**If you have already retrieved the images**, just load the metadata file by only running the section below"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "filepath = os.path.join(os.getcwd(), 'data', sitename)\n",
    "with open(os.path.join(filepath, sitename + '_metadata' + '.pkl'), 'rb') as f:\n",
    "    metadata = pickle.load(f) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Shoreline extraction\n",
    "\n",
    "Maps the position of the shoreline on the satellite images. The user can define the cloud threhold (`cloud_thresh`) and select the spatial reference system in which he would like to output the coordinates of the mapped shorelines (`output_epsg`). See http://spatialreference.org/ to find the EPSG number corresponding to your local coordinate system. To quality control each shoreline detection and manually validate the mapped shorelines, the user has the option to set the parameter `check_detection` to **True**. The other parameters are for advanced users only and are described in the last section of the README."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "settings = { \n",
    "    # general parameters:\n",
    "    'cloud_thresh': 0.2,        # threshold on maximum cloud cover\n",
    "    'output_epsg': 28356,       # epsg code of spatial reference system desired for the output   \n",
    "    # quality control:\n",
    "    'check_detection': True,    # if True, shows each shoreline detection to the user for validation\n",
    "\n",
    "    # add the inputs defined previously\n",
    "    'inputs': inputs,\n",
    "    \n",
    "    # [ONLY FOR ADVANCED USERS] shoreline detection parameters:\n",
    "    'min_beach_area': 4500,     # minimum area (in metres^2) for an object to be labelled as a beach\n",
    "    'buffer_size': 150,         # radius (in metres) of the buffer around sandy pixels considered in the shoreline detection\n",
    "    'min_length_sl': 200,       # minimum length (in metres) of shoreline perimeter to be valid \n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [OPTIONAL] Save .jpg of the satellite images \n",
    "Saves .jpg files of the preprocessed satellite images (cloud masking + pansharpening/down-sampling) under *./data/sitename/jpeg_files\\preprocessed*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "SDS_preprocess.save_jpg(metadata, settings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### [OPTIONAL] Digitize a reference shoreline\n",
    "Creates a reference shoreline which helps to identify outliers and false detections. The reference shoreline is manually digitised by the user on one of the images. The parameter `max_dist_ref` defines the maximum distance from the reference shoreline (in metres) at which a valid detected shoreline can be. If you think that you shoreline will move more than the default value of 100 m, please change this parameter to an appropriate distance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reference shoreline already exists and was loaded\n"
     ]
    }
   ],
   "source": [
    "%matplotlib qt\n",
    "settings['reference_shoreline'] = SDS_preprocess.get_reference_sl_manual(metadata, settings)\n",
    "settings['max_dist_ref'] = 100 # max distance (in meters) allowed from the reference shoreline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Batch shoreline detection\n",
    "Extracts the shorelines from the images. The mapped shorelines are saved into `output.pkl` (under *./data/sitename*) which contains the shoreline coordinates for each date in the spatial reference system specified by the user in `'output_epsg'`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "%matplotlib qt\n",
    "output = SDS_shoreline.extract_shorelines(metadata, settings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Plot the shorelines\n",
    "\n",
    "Simple plot of the mapped shorelines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x23a4f91b6a0>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.axis('equal')\n",
    "plt.xlabel('Eastings')\n",
    "plt.ylabel('Northings')\n",
    "for satname in output.keys():\n",
    "    if satname == 'meta':\n",
    "        continue\n",
    "    for i in range(len(output[satname]['shoreline'])):\n",
    "        sl = output[satname]['shoreline'][i]\n",
    "        date = output[satname]['timestamp'][i]\n",
    "        plt.plot(sl[:,0], sl[:,1], '.', label=date.strftime('%d-%m-%Y'))\n",
    "plt.legend()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.7"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}