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.

models.px.DLWP	Deep learning weather prediction (DLWP) prognostic model.
models.px.FCN	FourCastNet global prognostic model.
models.px.FengWu	FengWu (operational) weather model consists of single auto-regressive model with a time-step size of 6 hours.
models.px.FuXi	FuXi weather model consists of three auto-regressive U-net transfomer models with a time-step size of 6 hours.
models.px.Pangu24	Pangu Weather 24 hour model.
models.px.Pangu6	Pangu Weather 6 hour model.
models.px.Pangu3	Pangu Weather 3 hour model.
models.px.Persistence	Persistence model that generates a forecast by applying the identity operator on the initial condition and indexing the lead time by 6 hours.
models.px.SFNO	Spherical Fourier Operator Network global prognostic model.
models.px.StormCast	StormCast generative convection-allowing model for regional forecasts consists of two core models: a regression and diffusion model. Model time step size is 1 hour, taking as input: - High-resolution (3km) HRRR state over the central United States (99 vars) - High-resolution land-sea mask and orography invariants - Coarse resolution (25km) global state (26 vars) The high-resolution grid is the HRRR Lambert conformal projection Coarse-resolution inputs are regridded to the HRRR grid internally.

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.

models.dx.CorrDiffTaiwan	CorrDiff is a Corrector Diffusion model that learns mappings between low- and high-resolution weather data with high fidelity.
models.dx.ClimateNet	Climate Net diagnostic model, built into Earth2Studio.
models.dx.PrecipitationAFNO	Precipitation AFNO diagnsotic model.
models.dx.Identity	Identity diagnostic that is coordinate insensitive.

earth2studio.models: Utilities

models.auto.Package	A generic file system abstraction with local caching, uses Fsspec WholeFileCacheFileSystem to manage files.
models.batch.batch_func	Batch utility decorator which can be added to prognostic and diagnostic models to help enable support for automatic batching of data.