ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
PhysicsNeMo Checkpoints: AFNO_DX_SR-V1-ERA5
Model
NVIDIA
NVIDIA
PhysicsNeMo Checkpoints: AFNO_DX_SR-V1-ERA5

This deep learning model, based on the Adaptive Fourier Neural Operator framework (AFNO), predicts 6-hour accumulated surface solar irradiance given 24 atmospheric variables plus invariants.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application & Domain:Weather, Energy Forecasting
Model Type:Adaptive Fourier Neural Operator (AFNO)
Intended User:Weather and energy scientists or practitioners accelerating predictions using AI.
Output:Tensor (1 variable - 6-hour accumulated Surface Solar Irradiance).
Describe how the model works:AFNO decodes input variables into a latent space and learns coupling with the output variable - surface solar irradiance.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:N/A
Technical Limitations:The model may perform poorly for systems that are not similar to those in the training data, namely for rare weather phenomena or weather behavior outside of the 1980-2016 training dataset. There is no mechanism to enforce physical consistency for predictions.
Verified to have met prescribed NVIDIA quality standards:Yes
Performance Metrics:Root Mean Square Error (RMSE), Accuracy (ACC), and Bias (mean error).
Potential Known Risks:This model may inaccurately predict surface solar irradiance given technical limitations noted above.
Licensing:NVIDIA Community Model License