FuXi-CFD-model

FuXi-CFD Model

Overview

This repository accompanies the paper:

Reconstructing fine-scale 3D wind fields with terrain-informed machine learning

It provides the pre-trained FuXi-CFD model used in the study, exported in ONNX format, together with a complete inference example.

Version: v1.0
Framework: ONNX (runtime inference)

---

Model Description

FuXi-CFD is a terrain-informed deep learning model designed to reconstruct fine-scale three-dimensional wind fields from coarse atmospheric inputs and high-resolution terrain information.

Model Inputs

The model expects an inputs.npz file containing:

• dem — terrain elevation (300 × 300, float32, meters)
• roughness — surface roughness length (300 × 300, float32, meters)
• u_100m — coarse zonal wind at 100 m (9 × 9, float32, m s⁻¹)
• v_100m — coarse meridional wind at 100 m (9 × 9, float32, m s⁻¹)

All variables must be provided in physical units (no normalization applied by the user).
Normalization parameters used during training are included in normalization/.

Model Outputs

The model produces a file prediction.npz containing:

• u — zonal wind component (27, 300, 300), m s⁻¹
• v — meridional wind component (27, 300, 300), m s⁻¹
• w — vertical wind component (27, 300, 300), m s⁻¹
• k — turbulent kinetic energy (27, 300, 300), m² s⁻²

The vertical levels correspond to the 27 non-uniform heights described in the associated dataset documentation.

---

Quick Start (Inference Example)

cd inference_example
python scripts/infer.py \
  --model ../model/fuxicfd_model.onnx \
  --input data/inputs.npz \
  --output data/prediction.npz

Outputs are saved as data/prediction.npz with keys: u, v, w, k.

---

Repository Structure

• model/ — exported ONNX weights
• inference_example/ — complete preprocessing → inference → postprocessing pipeline
  • normalization/ — training-time normalization parameters
  • scripts/ — runnable inference scripts
  • utils/ — helper functions

---

License

CC BY-NC 4.0

---

Citation

If you use this model, please cite:

Lin, C., et al. Reconstructing fine-scale 3D wind fields with terrain-informed machine learning, Nature Communications (2026).