A JavaScript code developed in Google Earth Engine (GEE) Platform to Detect Flooded Area along with Affected Population

This GitHub repository contains the machine learning models described in Edoardo Nemnni, Joseph Bullock, Samir Belabbes, Lars Bromley Fully Convolutional Neural Network for Rapid Flood Segmentation in Synthetic Aperture Radar Imagery.

This repository contains a Jupyter Notebook for automatic flood extent mapping using space-based information.

Analyzing NYC's Stormwater Flood Map - Extreme Flood Scenario

Seamless Flood Mapping Using Harmonized Landsat and Sentinel-2 Data

A Collection of Flood Hazard Layers for New York City.

This repository includes an automatic statistical-based flood mapping approach for ALOS2 Level 2.1 data. Additionally, this method of flood extraction utilizes Google Earth Engine's open data and processing capabilities.

A Collection of NASA ARSET Courses for Flood Mapping and Synthetic Aperture Radar (SAR)

In this repository, I share a class project in which I explored the Google Earth engine sentinel 1 SAR dataset potential to be used for flood mapping of the 2019 Gorgan flood.

Georgia Tech CS 7643 (Deep Learning) Final Project: Flood Mapping Semantic Segmentation using a U-Net Model with Feature Representations of Sentinel-1 and Sentinel-2 Data

Improving Seamless Flood Mapping with Cloudy Satellite Imagery via Water Occurrence and Terrain Data Fusion

Intelligent Data Solution - Disaster Risk Reduction is a system to assist flood management in the state of Assam through data-driven ways. The repository contains codes to extract relevant datasets and the modelling approach used to calculate Risk Scores for each revenue circle in Assam.

A remote-sensing based application using Google Earth Engine for flood mapping and impact assessment.

Geospatial flood risk mapping pipeline using DEM data. Identifies flood-prone areas, generates masks & polygons, with DVC/S3 storage and Docker deployment.

Submission for Kenguruji team for Arnes Hackathon 2024

Flood extent mapping using Sentinel-1 SAR and a reproducible geospatial ML workflow

We are using Sentinel-2 satellite imagery and a specialized U-Net deep learning model to detect changes in landscapes before and after flood events. Using the OMBRIA dataset, the model reliably identifies flooded areas to support disaster management and response efforts.

Spatial flood vulnerability analysis in Bandung City using GIS-based scoring and Python for flood risk zonation.

Semantic segmentation for flood extent mapping from SAR satellite imagery