HASTE - High-speed Assessment and Satellite Tracking for Emergencies

Welcome to the HASTE (High-speed Assessment and Satellite Tracking for Emergencies) documentation.

HASTE is an AI-powered disaster assessment framework that leverages satellite imagery and remote sensing data to provide rapid assessment capabilities for humanitarian response teams.

Features

• Automated Disaster Assessment: AI-powered analysis of satellite imagery for damage assessment

• Multi-Source Imagery Support: Compatible with various satellite imagery providers (Vantor, Planet)

• Real-time Processing: Fast processing of pre and post-event imagery with Cloud Optimized GeoTIFF (COG) output

• Web Interface: User-friendly React-based interface for project management, labeling, and visualization

• Azure Cloud Integration: Scalable cloud-based processing with Azure Functions, Azure Batch, Blob Storage, and Data Lake

• ML Training & Inference: End-to-end model training and inference pipelines with GPU support via Azure Batch

• Tile Serving: Built-in TiTiler-based tile server for serving Cloud Optimized GeoTIFFs

System Components

Component	Technology	Description
UI	React + Vite	Single-page app for project management, labeling, and visualization
REST API (hastefuncapi)	Python Azure Functions	HTTP endpoints for CRUD operations
Queue Workers (hastefuncqueues)	Python Azure Functions	Queue-triggered functions for async processing
Tile Server (titilerfuncapi)	TiTiler + FastAPI	Cloud Optimized GeoTIFF tile serving
Core Library (hastegeo)	Python package	Shared models, processors, data layers, runners, and utilities

Where to start

• New to HASTE? Start with the User Guide to see how the application works end to end — creating projects, adding imagery, labeling, training a model, and viewing results.

• Want to run it locally? Follow Local Development to bring up the full stack with Docker Compose.

• Deploying to Azure? See the Deployment Guide for the one-step azd up deployment, and the Configuration Guide for the full settings matrix.