earth2studio.models: Models#
earth2studio.models.px: Prognostic#
Prognostic models are a class of models that perform time-integration. Thus are typically used to generate forecast predictions.
Warning
Pre-trained prognostic models provided in Earth2Studio may be provided under different licenses. We encourage users to familiarize themselves with each prior to use.
ACE2-ERA5 prognostic model wrapper. |
|
Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). |
|
Artificial Intelligence Forecasting System Ensemble (AIFS ENS v1.0), a probabilistic, ensemble-based forecast model from the European Centre for Medium-Range Weather Forecasts (ECMWF). |
|
Atlas prognostic model for ERA5 variables on a 0.25° global lat-lon grid. |
|
Aurora 0.25 degree global forecast model. |
|
Climate in a bottle video prognostic Climate in a Bottle (cBottle) is an AI model for emulating global km-scale climate simulations and reanalysis on the equal-area HEALPix grid. |
|
Wraps a prognostic model and one or more diagnostic models into a single prognostic model. |
|
DLESyM-V1-ERA5 prognostic model. |
|
DLESyM prognostic model supporting lat/lon input and output coordinates. |
|
Deep learning weather prediction (DLWP) prognostic model. |
|
FourCastNet global prognostic model. |
|
FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. |
|
FengWu (operational) weather model consists of single auto-regressive model with a time-step size of 6 hours. |
|
FuXi weather model consists of three auto-regressive U-net transfomer models with a time-step size of 6 hours. |
|
GraphCast operational model |
|
GraphCast Small 1.0 degree model |
|
ModAFNO interpolation for global prognostic models. |
|
Pangu Weather 24 hour model. |
|
Pangu Weather 6 hour model. |
|
Pangu Weather 3 hour model. |
|
Persistence model that generates a forecast by applying the identity operator on the initial condition and indexing the lead time by 6 hours. |
|
Spherical Fourier Operator Network global prognostic model. |
|
StormCast generative convection-allowing model for regional forecasts consists of two core models: a regression and diffusion model. |
|
StormScope model forecasting GOES data on the HRRR grid. |
|
StormScope model forecasting MRMS data on the HRRR grid. |
earth2studio.models.dx: Diagnostic#
Diagnostic models are a class of models that do not perform time-integration. These may be used to map between weather/climate variables to other quantities of interest, used to enbable additional analysis, improve prediction accuracy, downscale, etc.
Warning
Pre-trained diagnostic models provided in Earth2Studio may be provided under different licenses. We encourage users to familiarize themselves with each prior to use.
Climate in a bottle infill diagnostic Climate in a Bottle (cBottle) is an AI model for emulating global km-scale climate simulations and reanalysis on the equal-area HEALPix grid. |
|
Climate in a Bottle Super-Resolution (CBottleSR) model. |
|
Climate in a Bottle tropical cyclone guidance diagnostic. |
|
CMIP6 to ERA5 downscaling model based on the CorrDiff architecture. |
|
CorrDiff is a Corrector Diffusion model that learns mappings between low- and high-resolution weather data with high fidelity. |
|
Climate Net diagnostic model, built into Earth2Studio. |
|
Calculates the relative humidity (RH) from specific humidity and temperature for specified pressure levels. |
|
Calculates the surface relative humidity (RH) from dewpoint temperature and air temperature. |
|
Interpolates the surface pressure in hPa from pressure level geopotential, surface geopotential and optionally temperature. |
|
Calculates the Total Column Water Vapor (TCWV) from specific humidity at pressure levels and surface pressure. |
|
Calculates the Vapor Pressure Deficit (VPD) in hPa from relative humidity and temperature fields. |
|
Calculates the Wind Speed (WS) magnitude from eastward and northward wind components for specified levels. |
|
Precipitation AFNO diagnsotic model. |
|
Improved Precipitation AFNO diagnostic model. |
|
Solar Radiation AFNO diagnostic model for 1-hour frequency predictions. |
|
Solar Radiation AFNO diagnostic model for 6-hour frequency predictions. |
|
Finds a list of tropical cyclone (TC) centers using an adaption of the method described in the conditions in Wu and Duan 2023. |
|
Finds a list of tropical cyclone centers using the conditions in Vitart 1997 |
|
Wind gust AFNO diagnsotic model. |
|
Identity diagnostic that is coordinate insensitive. |
earth2studio.models.da: Data Assimilation#
Data assimilation models are a class of models that incorporate observational data into model states or grids. These models process sparse, irregularly-distributed observations (typically from DataFrames) and map them to regular grids or model coordinate systems (typically as DataArrays). Data assimilation models support both stateless and stateful operation, allowing them to process observations independently or maintain internal state across time steps.
Warning
Data Assimilation models are a new addition to Earth2Studio and APIs might be subject to change without warning while the implementation is hardened.
Interpolation assimilation model that interpolates sparse observations to a lat-lon grid. |
|
StormCast with score-based data assimilation (SDA) using diffusion posterior sampling for convection-allowing regional forecasts. |
earth2studio.models: Utilities#
A generic file system abstraction with local caching, uses Fsspec WholeFileCacheFileSystem to manage files. |
|
Batch utility decorator which can be added to prognostic and diagnostic models to help enable support for automatic batching of data. |