Overview of HYDRAFloods processing

​

​

​

20/04/2023

HYDRAFloods Training

OUTLINE

​

• HYDRAFloods background
• What is HYDRAFloods?
• Example uses
• Exercise

​

HYDRAFloods Training

2

2020-11-30

HYDRAFloods Background

HYDRAFloods Training

3

• Water maps from many institutions lead to information overload
• Different data and methods used
• Limited access to information on how maps were created
• Methods are not available for others (closed source)

Challenges

​

2020-11-30

HYDRAFloods Background

HYDRAFloods Training

4

• Cloudy conditions during rainy season render optical imagery useless
• Many sensors are required to monitor flood events
• Maps generated using individual data tiles = smaller coverage area
• Data volume
• One Sentinel 1 scene is ~1 GB in size at ~10 m spatial resolution!!!

Challenges

​

2020-11-30

HYDRAFloods Background

HYDRAFloods Training

5

• HYDrologic Remote sensing Analysis for Floods
• Open source - anyone can use/modify for free
• Documented to increase transparency
• Cloud-based - overcome big data challenges
• End-to-End processing - users have all the tools needed to create their own high quality surface water map
• Leverage multiple sensors easily with common syntax and data fusion workflows

Solution - HYDRAFloods

2020-11-30

What is HYDRAFloods

HYDRAFloods Training

6

• Open source - anyone can use/modify for free

2020-11-30

What is HYDRAFloods

HYDRAFloods Training

7

• Documented to increase transparency

​

2020-11-30

What makes HYDRAFloods powerful?

• Is built in GEE and Python for end-user ease of use

​

• Flood Maps can be generated from an array of sensors
• Making it powerful to combat temporal gaps

What is HYDRAFloods

HYDRAFloods Training

9

• End-to-End processing - users have all the tools needed to create their own high quality surface water map
• QA masking
• SAR speckle filters
• Terrain correction (SAR and Optical)
• Time series processing
• Machine learning workflows
• Multi-sensor water mapping algorithms

2020-11-30

What is HYDRAFloods

HYDRAFloods Training

10

• Leverage multiple sensors easily with common syntax and data fusion workflows

2020-11-30

HYDRAFloods S-1 Flood detection workflow

Background: Science

• Single sensor (flood) maps
• Sentinel-1
• Sentinel-2
• Landsat 8
• Daily data fused (flood) maps

Otsu

QA UNet

based on Donchyts et al. (2016), Application: Markert et al. (2020)

based on Hughes et al. (2019), Application: Mayer et al. (2021)

all

optical

Thresholding Algorithm

Otsu’s Thresholding

• Automated histogram-based thresholding approach
• Maximizes inter-class variance between two classes
• Assumes there are only two classes, a background and foreground

Markert et al. (2020)

Hurricanes Eta & Iota

Central America example of flood detected from Sentinel-1 using HYDRAFloods

Example Uses

HYDRAFloods Training

15

WFP Cambodia

• Currently providing combined water maps from multiple sensors
• Provide multi sensor surface water maps
• Uses machine learning and deep learning methods

https://www.humanitarianresponse.info/sites/www.humanitarianresponse.info/files/documents/files/hrf_sitrep_no6_26-oct-20.pdf

2020-11-30

Example Uses

HYDRAFloods Training

16

Hurricane Eta & Iota

• Automated processing of Sentinel 1 data when available
• Data provided to CEPREDENAC for response efforts

Flooding in Mexico 2020-11-21

2020-11-30

Example Uses

HYDRAFloods Training

17

Deltares Flood Impact Analysis on Road Networks

• Used to understand how floods can potentially affect road networks and peoples access to critical services

https://storymaps.arcgis.com/stories/9a130a0e8c424dceb91a42839662c1f3

2020-11-30

Exercise

Water mapping exercise:

https://colab.research.google.com/drive/1bSo1bRxpt78R91febjS5cxA1byBk9F0j?usp=sharing

HYDRAFloods Training

18

2020-11-30

Thank you for your attention!

HYDRAFloods Training