damage-assessment

Damage parameter estimation for ancient DNA

3DAeroRelief is a high-resolution 3D point cloud benchmark dataset designed for semantic segmentation in post-disaster scenarios. It includes 3D data for eight distinct areas, COLMAP configuration files for reconstruction, and Python utility scripts for merging and processing semantic labels and geometry.

Flood mapping and damage assessment in GEE

This repository provides a tutorial and code for reproducing the data and results presented in the following publication: Automated Mapping of Post-Storm Roof Damage Using Deep Learning and Aerial Imagery: A Case Study in the Caribbean (Kucharczyk, Nesbit, & Hugenholtz, 2025, Remote Sensing).

This repository houses a comprehensive deep learning-based system for the scene classification of very high-resolution satellite imagery, focusing on post-earthquake damage assessment. The primary case study involves the devastating earthquakes that occurred in Kahramanmaraş province, Türkiye, in 2023.

MATLAB code to generate some results on the paper (Kitayama, & Cilsalar, 2022).

Building machine learning models that predict the damage level caused by an earthquake on a building using the Nepal's Earthquake dataset

Sheldon K. Salmon — AI Reliability Architect. Creator of the AION Constitutional Stack and the CERTUS engine — epistemic scoring that says how much to trust crisis data, and how much to trust the score. Code is open source. The judgment is not.

Building-level war-damage mapping for El Geneina (West Darfur, 2023) from Sentinel-1 InSAR coherence change detection.

Multi-Head Convolutional Networks for Post Earthquake Damage Assessment of Damaged Buildings

Repository for the paper "Improved Integrated Framework for Flooded Crop Damage and Recovery Assessment: A Multi-Source Earth Observation and Participatory Mapping in Hadejia, Nigeria"

An AI-powered web application that analyzes vehicle images to detect damage, estimate severity, and suggest repair costs using a vision-language model.

An AI-powered web application that analyzes vehicle images to detect damage, estimate severity, and suggest repair costs using a vision-language model.

Unofficial, beta. Two coverage measurements over California's public wildfire datasets, published as counts: FRAP's historical fire perimeters and CAL FIRE's DINS damage inspections. Each operationalizes a limitation the publisher already states, so a code meaning unknown is never counted as a recorded value.

Post-Disaster Damage Assessment

Guided Team Challenge 2021: Exposure Team Project

AI-powered satellite damage assessment map for before/after imagery, UNOSAT data, and battle damage review.

An AI-powered web application that analyzes vehicle images to detect damage, estimate severity, and suggest repair costs using a vision-language model.

AIMGroup is marine cargo ship surveyors and consultant with expertise on class and risk managing on seaworthiness and tecnical condition.