Automate stochastic wind field simulations across JAX, NumPy, and PyTorch backends.
npx skills add https://github.com/NanxiiChen/wind-simulation-GPU --skill wind-sim
Please help me install this Agent Skill. Skill: wind-sim Source: https://github.com/NanxiiChen/wind-simulation-GPU/tree/main Command: npx skills add https://github.com/NanxiiChen/wind-simulation-GPU --skill wind-sim
Automates end-to-end stochastic wind field simulations across GPU and CPU backends, enabling researchers and developers to run, benchmark, and validate wind field models without manual orchestration.
Run a stationary wind field simulation using the default config to generate sample output.
High-intent search queries and answers about installing and using this skill.
Stochastic wind field simulations can be run across JAX, NumPy, and PyTorch backends using a unified API. This automates workflows for stationary and nonstationary models without manual orchestration.
GPU-accelerated stochastic wind simulation is used to run, benchmark, and validate wind field models. It enables researchers to compare simulations against theory using PSDs and cross-correlation analysis.
Yes, the wind simulation workflow supports JAX, PyTorch, and NumPy backends. It provides a unified API and backend-agnostic spectrum models to run across different hardware accelerators.
The best way to benchmark wind field performance is using a config-driven CLI workflow with ml_collections ConfigDict. This allows rapid experimentation and performance validation across GPU and CPU backends.
Yes, you can customize wind simulation parameters using CLI overrides on the default config. This config-driven workflow leverages ml_collections ConfigDict for rapid experimentation without code changes.
Automated wind field simulation workflows may not suit scenarios outside stationary and nonstationary wind engineering research. It requires a multi-backend architecture and dependencies like JAX or NumPy to function correctly.
yonesukeSolve Ax=b linear systems with NumPy, JAX, PyTorch, and Lineax backends.
huangzesenAnalyze Parker Solar Probe data on magnetic switchbacks, heating, and intermittency.
SunS1eep1ngCreate static, animated, and interactive plots with Matplotlib and NumPy.
plurigridGenerate deterministic colors across CPU and GPU with SplitMix64 PRNG.
