Three natural-hazard prediction systems from one field equation. Prospective forecasts frozen and hash-receipted before outcomes (Ed25519-signed from 2026-07-31), scored honestly against named baselines - every number resolves to a committed artifact, never to this description.
Desktop app that maps live hurricanes, floods, tornado warnings on a satellite map, plus an archive of record weather events.
Tracks Accumulated Cyclone Energy (ACE) for the Atlantic & Eastern Pacific hurricane seasons from NOAA HURDAT2 data. Live dashboard, season history, and records at aceofcanes.com.
Trust the view that sees the target: visibility-conditioned reliability gating for conflict-aware cross-view disaster damage assessment (wildfire + hurricane, street-view x satellite).
Natural Disaster Hazards Analysis from satellite imagery - unified PyTorch pipeline: 13+9 disaster domains, 24 benchmarks, 34 models, Colab demos, ONNX export. Maintained by Syed Rafi Ahmed | extends the AnyDisaster benchmark (Chen et al. 2026).
StormDPS is a real-time tropical cyclone analysis tool that computes a Destructive Potential Index using NOAA/NHC data, Integrated Kinetic Energy modeling, storm surge estimates, and regional economic vulnerability analysis. It covers all global basins, features historical storm comparisons, and delivers live weather intelligence for every consumer
Open-source Caribbean observatory · 170 years of NOAA hurricane data · USGS earthquakes · Climate trends & AI prediction
MCP servers for coastal oceanography
Personal "vibecoded" side project
NOAA/NHC tropical cyclone sensors and bundled dynamic dashboard card for Home Assistant
NHC hurricane cone card for Home Assistant
Local storm viewer for Google DeepMind WeatherNext 3 hurricane forecasts: 64-member tracks, NHC cone & warnings, live radar
Code for Reliability and Resilience Implications of Data-Center Demand and Emergency Support in Distribution Systems: supply adequacy, hurricane support, internal service, and export economics.
A unified interface to access tropical cyclone best-track datasets in different formats.
Interactive hurricane impact analysis dashboard for UNICEF. Visualizes probabilistic and deterministic hurricane forecasts, assessing risk to population, schools, health centers, and infrastructure. Built with Dash and powered by the giga-spatial package for geospatial data processing.
Command-line tool and Discord bot which presents ATCF and Best Track data.
Open, tidy database of FEMA Hazus flood and hurricane damage/vulnerability curves — 278k curves, full provenance, one-command install into SQLite/DuckDB/PostgreSQL/Snowflake
A full-screen, location-aware weather kiosk for Raspberry Pi / Windows — search any city for live radar, all-basin tropical tracking, and real-time lightning, composited in PyQt6.
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).
Location-level Florida hurricane catastrophe model in Python: HURDAT2-calibrated hazard + physical wind field (Holland, Vickery-Wadhera, Kaplan-DeMaria), synthetic exposure, HAZUS-anchored vulnerability, OED/YLT/ELT formats, XoL reinsurance with reinstatements, gross/net AEP/OEP curves & PMLs, historical backtesting (Andrew, Ian).
To associate your repository with the hurricane topic, visit your repo's landing page and select "manage topics."