Models

Browse PyHazards model implementations across hazard families, compare scope and maturity, and navigate to model-specific detail pages.

At a Glance

Hazard Families

4

Catalog tabs grouped by the normalized public hazard taxonomy.

Implemented Models

24

Public core baselines plus additional implemented variants.

Experimental Adapters

3

Prototype weather-model integrations kept separate from the stable catalog.

Benchmark-linked Models

27

Models with explicit benchmark-family or ecosystem links on this page.

Catalog by Hazard

Use the hazard tabs below to browse the public catalog. Each card keeps the index-page summary short, then links into model-specific detail pages and compatible benchmark coverage.

Wildfire models cover danger forecasting, weekly activity forecasting, and spread prediction under the shared wildfire benchmark family.

Implemented Models

This table includes both core baselines and public variants or additional implementations for the hazard family.

ASUFM

A temporal convolution baseline for weekly wildfire activity forecasting.

Wildfire Forecasting Implemented

Details: ASUFM

Benchmark Family: Wildfire Benchmark

DNN-LSTM-AutoEncoder

A two-stage wildfire framework with a DNN stage for incident-level cause and size prediction plus an LSTM + autoencoder stage for weekly forecasting.

Wildfire Classification Forecasting Implemented

Benchmark Family: Wildfire Benchmark

FireCastNet

A compact encoder-decoder baseline for wildfire spread mask prediction.

Wildfire Spread Implemented

Details: FireCastNet

Benchmark Family: Wildfire Benchmark

Benchmark Ecosystems: WildfireSpreadTS

ForeFire Adapter

A lightweight simulator-style wildfire spread adapter inspired by front-propagation systems.

Wildfire Spread Implemented

Details: ForeFire Adapter

Benchmark Family: Wildfire Benchmark

Benchmark Ecosystems: WildfireSpreadTS

Wildfire Forecasting

A sequence forecasting baseline for next-window wildfire activity across weekly count features.

Wildfire Forecasting Implemented

Benchmark Family: Wildfire Benchmark

WildfireSpreadTS

A temporal convolution wildfire spread baseline over short raster history windows.

Wildfire Spread Implemented

Details: WildfireSpreadTS

Benchmark Family: Wildfire Benchmark

Benchmark Ecosystems: WildfireSpreadTS

WRF-SFIRE Adapter

A lightweight raster wildfire spread adapter inspired by WRF-SFIRE style transport.

Wildfire Spread Implemented

Benchmark Family: Wildfire Benchmark

Benchmark Ecosystems: WildfireSpreadTS

CNN-ASPP

An explainable CNN segmentation model with an ASPP mechanism for next-day wildfire spread prediction.

Wildfire Spread Implemented

Details: CNN-ASPP

Benchmark Family: Wildfire Benchmark

Benchmark Ecosystems: WildfireSpreadTS

Earthquake models span phase picking and dense-grid forecasting, with detail pages linked to the shared earthquake benchmark coverage.

Implemented Models

This table includes both core baselines and public variants or additional implementations for the hazard family.

EQNet

A transformer-style earthquake phase-picking baseline for modern sequence modeling comparisons.

Earthquake Phase Picking Implemented

Details: EQNet

Benchmark Family: Earthquake Benchmark

Benchmark Ecosystems: SeisBench

EQTransformer

A bidirectional sequence encoder for joint earthquake phase picking with attention pooling over waveform windows.

Earthquake Phase Picking Implemented

Details: EQTransformer

Benchmark Family: Earthquake Benchmark

Benchmark Ecosystems: pick-benchmark

GPD

A compact CNN baseline for generalized phase detection and historical earthquake picking comparisons.

Earthquake Phase Picking Implemented

Details: GPD

Benchmark Family: Earthquake Benchmark

Benchmark Ecosystems: pick-benchmark

PhaseNet

A lightweight phase-picking baseline that predicts P- and S-arrival indices from multichannel waveform windows.

Earthquake Phase Picking Implemented

Details: PhaseNet

Benchmark Family: Earthquake Benchmark

Benchmark Ecosystems: SeisBench

WaveCastNet

A ConvLEM-based sequence-to-sequence model for dense-grid earthquake wavefield forecasting and early-warning style rollout experiments.

Earthquake Wavefield Forecasting Implemented

Details: WaveCastNet

Benchmark Family: Earthquake Benchmark

Benchmark Ecosystems: AEFA, pyCSEP

Flood models cover streamflow and inundation forecasting, ranging from sequence baselines to dense-grid flood-mapping architectures.

Implemented Models

This table includes both core baselines and public variants or additional implementations for the hazard family.

EA-LSTM

An entity-aware hydrology baseline with static-feature gating over streamflow histories.

Flood Streamflow Implemented

Details: EA-LSTM

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: WaterBench

FloodCast

A compact spatiotemporal flood-inundation baseline for raster forecast experiments.

Flood Inundation Implemented

Details: FloodCast

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: FloodCastBench

Google Flood Forecasting

A transformer-style sequence baseline for nodewise streamflow forecasting.

Flood Streamflow Implemented

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: Caravan

NeuralHydrology LSTM

An adapter-style LSTM baseline for nodewise streamflow forecasting on graph-temporal inputs.

Flood Streamflow Implemented

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: Caravan

UrbanFloodCast

A U-Net style urban inundation baseline for dense-grid flood prediction.

Flood Inundation Implemented

Details: UrbanFloodCast

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: FloodCastBench

HydroGraphNet

A physics-informed graph neural network for flood forecasting with interpretable KAN-style components, residual message passing, and delta-state decoding.

Flood Streamflow Implemented

Details: HydroGraphNet

Benchmark Family: Flood Benchmark

Benchmark Ecosystems: HydroBench

Storm models are organized under one tropical-cyclone family, including basin-specific hurricane baselines and shared all-basin forecasting models.

Implemented Models

This table includes both core baselines and public variants or additional implementations for the hazard family.

Hurricast

A compact multimodal storm baseline for hurricane track and intensity forecasting.

Tropical Cyclone Track + Intensity Implemented

Details: Hurricast

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: IBTrACS

SAF-Net

A spatiotemporal tropical-cyclone baseline with an intensity-focused head and shared trajectory output.

Tropical Cyclone Track + Intensity Implemented

Details: SAF-Net

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: TCBench Alpha

TCIF-fusion

A knowledge-guided fusion baseline for tropical cyclone track and intensity forecasting.

Tropical Cyclone Track + Intensity Implemented

Details: TCIF-fusion

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: TCBench Alpha

Tropical Cyclone MLP

A compact MLP baseline for hurricane track and intensity forecasting.

Tropical Cyclone Track + Intensity Implemented

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: TCBench Alpha

TropiCycloneNet

A GRU plus attention baseline for all-basin tropical cyclone forecasting.

Tropical Cyclone Track + Intensity Implemented

Details: TropiCycloneNet

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: TropiCycloneNet-Dataset

Experimental Adapters

These entries remain public as lightweight wrapper or prototype integrations and should not be counted as stable implemented methods.

FourCastNet TC Adapter

An experimental wrapper-style storm adapter inspired by FourCastNet forecast fields.

Tropical Cyclone Track + Intensity Experimental Adapter

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: IBTrACS

GraphCast TC Adapter

An experimental wrapper-style storm adapter inspired by GraphCast/GenCast forecast fields.

Tropical Cyclone Track + Intensity Experimental Adapter

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: IBTrACS

Pangu TC Adapter

An experimental wrapper-style storm adapter inspired by Pangu-Weather forecast fields.

Tropical Cyclone Track + Intensity Experimental Adapter

Details: Pangu TC Adapter

Benchmark Family: Tropical Cyclone Benchmark

Benchmark Ecosystems: IBTrACS

Recommended Entry Points

If you are new to PyHazards, these four models provide the clearest starting point for each hazard family.

Wildfire

Start with: FireCastNet

A compact encoder-decoder baseline for wildfire spread mask prediction.

Benchmark: Wildfire Benchmark

Earthquake

Start with: PhaseNet

A lightweight phase-picking baseline that predicts P- and S-arrival indices from multichannel waveform windows.

Benchmark: Earthquake Benchmark

Flood

Start with: FloodCast

A compact spatiotemporal flood-inundation baseline for raster forecast experiments.

Benchmark: Flood Benchmark

Tropical Cyclone

Start with: Hurricast

A compact multimodal storm baseline for hurricane track and intensity forecasting.

Benchmark: Tropical Cyclone Benchmark

Programmatic Use

Use pyhazards.models package for the developer registry workflow, builder examples, and package-level API lookup. Use Benchmarks to compare compatible benchmark families before selecting a model for evaluation.