ML | U-Net
U-Net The U-Net architecture follows an encoder-decoder cascade structure, where the encoder gradually compresses information into a lower-dimensional representation. Then the decoder decodes this inf
ML | GNN Graph Neural Network Model
Overview of Graph Neural Networks (GNNs) Graph Neural Networks (GNNs) are a specialized type of neural network designed to process and analyze graph-structured data. Unlike traditional neural networks
ML | PyTorch
PyTorch 2017 年初由 Facebook 開源的另一套建立在 Torch 之上的深度學習框架 PyTorch 因其語法簡潔優雅、概念直觀和易上手的特性，甫推出便迅速走紅，儼然已成為瓜分深度學習市場的有力競爭者。 PyTorch is an optimized tensor library for deep learning using GPUs and CPUs. Automatic d
Maths | ROC Curves
ROC curve 在訊號檢測理論中，接收者操作特徵曲線，或者叫 ROC 曲線（Receiver operating characteristic curve），是一種坐標圖式的分析工具， 用於選擇最佳的訊號偵測模型 、 捨棄次佳的模型 或者 在同一模型中設置最佳閾值。 在做決策時，ROC分析能不受成本／效益的影響，給出客觀中立的建議。 ROC曲線 (Receiver operating ch
MPAS | Smagorinsky turbulence model | Eddy viscosity
Large eddy simulation (LES) Large eddy simulation (LES) is a mathematical model for turbulence used in computational fluid dynamics. It was initially proposed in 1963 by Joseph Smagorinsky to simulate
WRF | MPAS | MPI | halo/ghost cell
Message Passing Interface (MPI) 訊息傳遞介面（Message Passing Interface，縮寫MPI）是一個平行計算的應用程式介面（API），常在超級電腦、電腦叢集等非共用主記憶體環境程式設計。 The message passing interface effort began in the summer of 1991 when a small grou
MPAS | MPAS-A Idealized Test Cases
MPAS-Atmosphere idealized test cases https://mpas-dev.github.io/atmosphere/test_cases.html The downloads below for MPAS-Atmosphere idealized test cases include the following:
CFD | OpenFOAM | STL file | 網格生成
OpenFOAM三維網格生成器 snappyHexMesh（SHM）是OpenFOAM軟體的三維結構化網格生成模組，功能比較強大，設定靈活，表面處理貼合功能非常強健並且可以並行運算。 SHM能夠透過使用者自訂參數（如細化參數castellatedMeshControls、切合參數snapControls等）對預先載入的幾何體檔案（通常為'.stl'檔案）自動實現三維網格生成、加密(castella
