{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Authors:** Kleanthis Karamvasis \n",
"
FLOODPY: Mapping flooded regions of Daniel Flood event Greece, September 2023 "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"### Important:\n",
" Before running this notebook, please make sure that \n",
"1. you have successufully created floodpy_gpu conda environment based on [FLOODPY_gpu_env](FLOODPY_gpu_env.yml)\n",
"2. you have activated the floodpy_gpu conda environment for running this notebook \n",
"3. you have downloaded Floodvit model from https://www.dropbox.com/scl/fi/srw7u4cw1gtxrf4xzmsh7/floodvit.pt?rlkey=snskpq1qrdav5u2jya8k2bocg&e=1&dl=0\n",
" \n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# NOTEBOOK INTRODUCTION\n",
"\n",
"### Data used\n",
"\n",
"| Product Name | Description | Usage | Access Link |\n",
"|:--------------------:|:-----------------:|:-----------------:|:-----------------:|\n",
"| ERA5 | ERA5 is the fifth generation ECMWF reanalysis for the global climate and weather for the past 4 to 7 decades. ERA5 provides hourly estimates for a large number of atmospheric, ocean-wave and land-surface quantities. Data has been regridded to a regular lat-lon grid of 0.25 degrees for the reanalysis. ERA5 is updated daily with a latency of about 5 days. | Precipitation | link |\n",
"| Sentinel-1 GRD | The Sentinel-1 mission comprises a constellation of two polar-orbiting satellites, operating day and night performing C-band synthetic aperture radar imaging, enabling them to acquire imagery regardless of the weather. | Backscatter changes | link |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Learning outcomes\n",
"\n",
"At the end of this notebook you will be able to identify flooded regions from Sentinel-1 data using FloodPy. Be aware that the estimated run time of the notebook depends on your **area of interest**, your **temporal span of interest** and your network **download speed**."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Outline\n",
"\n",
"Floods are considered the second gravest disaster for the agricultural sector. The increasing intensity and the frequency of flood events can result to significant yield losses. In the present notebook, we present a ViT-based (Visual Transformer) approach (Bountos et al., 2023) to extract flooded area based on multitemporal Sentinel-1 intensity observations.\n",
"FLOOD PYthon toolbox is a free and open-source python toolbox for mapping of floodwater. FLOODPY requires a specified time of interest related to the flood event and corresponding geographical boundaries. We believe that the produced maps with delineated flood-affected agricultural fields can be helpful for governments, insurers and disaster response agencies to improve flood risk assessment, relief targeting, and ultimately to protect climate-vulnerable communities from floods. \n",
"\n",
"References:\n",
"\n",
"\n",
" \n",
"Bountos, N. I., Sdraka, M., Zavras, A., Karasante, I., Karavias, A., Herekakis, T., ... & Papoutsis, I. (2023). Kuro Siwo: 12.1 billion $ m^ 2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping. arXiv preprint [paper link](https://arxiv.org/abs/2311.12056) [github link](https://github.com/Orion-AI-Lab/KuroSiwo)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
" \n",
"##
Contents\n",
"\n",
"
\n",
"\n",
"##
1. Flood event description\n",
"[Back to top](#TOC_TOP)\n",
"\n",
"
\n",
"\n",
"##
2. Set input parameters for FLOODPY\n",
"[Back to top](#TOC_TOP)\n",
"\n",
"
\n",
"\n",
"#### Important: Please provide the path of the Floodvit model [link](https://www.dropbox.com/scl/fi/srw7u4cw1gtxrf4xzmsh7/floodvit.pt?rlkey=snskpq1qrdav5u2jya8k2bocg&e=1&dl=0)
"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"ViT_model_filename = '/home/kleanthis/Projects/Thessalia_Floods_2023/Vit_model/floodvit.pt'"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"params_dict = {'projectfolder':projectfolder,\n",
" 'flood_event':flood_event,\n",
" 'src_dir' : src_dir,\n",
" 'snap_orbit_dir' : snap_orbit_dir,\n",
" 'GPTBIN_PATH' : GPTBIN_PATH,\n",
" 'pre_flood_start' : pre_flood_start,\n",
" 'pre_flood_end' : pre_flood_end,\n",
" 'flood_start' : flood_start,\n",
" 'flood_end' : flood_end,\n",
" 'AOI_File' : AOI_File,\n",
" 'LONMIN' : LONMIN,\n",
" 'LATMIN' : LATMIN,\n",
" 'LONMAX' : LONMAX,\n",
" 'LATMAX' : LATMAX,\n",
" 'relOrbit' : relOrbit,\n",
" 'minimum_mapping_unit_area_m2' : minimum_mapping_unit_area_m2,\n",
" 'CPU' : CPU,\n",
" 'RAM' : RAM,\n",
" 'Copernicus_username' : Copernicus_username,\n",
" 'Copernicus_password' : Copernicus_password,\n",
" }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"##
3. Estimation of Flooded Area using Sentinel-1 data\n",
"[Back to top](#TOC_TOP)\n",
"
"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"Floodpy_app.plot_ERA5_precipitation_data()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"add_metadata(Floodpy_app_objs, Floodpy_app)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Select a single datetime for Interactive plotting"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Select a singe datetime for the following list:\n",
"2023-09-06 04:39:47.095652\n",
"2023-09-07 16:24:12.139701\n",
"2023-09-12 16:32:24.059385\n",
"2023-09-13 04:31:57.827516\n",
"2023-09-18 04:39:47.608904\n"
]
}
],
"source": [
"print(\"Select a singe datetime for the following list:\")\n",
"print(*list(Floodpy_app_objs.keys()),sep='\\n')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Example: plot_interactive_map(Floodpy_app_objs[pd.Timestamp('This should be replaced')])\n",
"plot_interactive_map(Floodpy_app_objs[pd.Timestamp('2023-09-07 16:24:12.139701')])"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "floodpy_gpu",
"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": "3.8.17"
}
},
"nbformat": 4,
"nbformat_minor": 2
}