WRF | MPAS | UCM and LCZs
WRF-UCM WRF-UCM refers to the Weather Research and Forecasting model (WRF) integrated with an Urban Canopy Model (UCM). This framework is designed to enhance the simulation of urban environments withi
ML | ResNet
殘差網路概述 殘差神經網路（Residual Neural Network，簡稱 ResNet ） 是一種深度學習模型，旨在解決傳統深度神經網路中常見的梯度消失和梯度爆炸問題。這種網路的核心理念是讓每一層學習與輸入之間的殘差，而非直接學習預期的輸出。這樣的設計使得訓練更深層的模型變得更為有效，並且在增加層數時能保持甚至提高準確率。 ResNet 透過 殘差學習解決了深度網路的退化問題，讓我們可以訓
ML | VAE Variational Auto-Encoder
基礎知識回顧 Latent Variable Variations Gaussian Mixture Model Gaussian Mixture Model，即高斯混合模型。生成模型比較主流的三個模型為：隱馬可夫模型HMM、樸素貝葉斯模型NB、高斯混合模型GMM。這裡我們主要為大家介紹GMM。 混合模型是一個可以用來表示在總體分佈中含有N個子分佈的機率模型，它表示了觀測資料在總體中的機率分
ML | ECMWF | Anemoi
Anemoi Anemoi is a collaborative and open-source framework for developing machine learning weather forecasting models. Named after the Greek gods of the winds, the goal of Anemoi is to provide the key
WRF | MPAS | README.physics_files
While browsing the WRF repository, I came across an introduction file in version 4.6.1, located at WRF/run/README.physics_files. This file provides a list of external files used by various physical sc
ML | set CUDA_HOME in a conda environment
set CUDA_HOME in a conda environment 123456micromamba install -c conda-forge cudatoolkit-devwhich nvccnvcc --versionecho $CUDA_HOMEexport CUDA_HOME=$CONDA_PREFIXecho $CUDA_HOME References How to set
NWP | Clear-sky vs. All-sky Approaches in NWP and DA
Clear-sky vs. All-sky Approaches in NWP and DA In the field of Numerical Weather Prediction (NWP) and Data Assimilation (DA), the clear-sky and all-sky approaches represent two different methodologies
MPAS | UXarray
UXarray Xarray extension for unstructured climate and global weather data analysis and visualization written around the UGRID conventions. Why? UXarray aims to address the geoscience community need fo
