Deep Learning Approach to Natural Convection Heat Transfer in a Cavity: A Simulation Dataset for Nano-Encapsulated Phase Change Material Suspensions

Published: 11 April 2023| Version 1 | DOI: 10.17632/j5f6r56jnb.1
Mohammad Edalatifar,
Mohammad Ghalambaz,


Big data images for natural convection flow and heat transfer (nano-encapsulated phase change suspensions) The related paper has been published here: Edalatifar, M., M.B. Tavakoli, and F. Setoudeh, A Deep Learning Approach to Predict the Flow Field and Thermal ‎Patterns of Nonencapsulated Phase Change Materials ‎Suspensions in an Enclosure‎. Journal of Applied and Computational Mechanics, 2021. Links: Keywords: Deep convolutional neural networks - Loss function - Heat transfer images - Physical images - Artificial intelligence - CFD - Computational fluids dynamics - Finite element method -Dirichlet boundary condition Nano-encapsulated phase-change suspension; natural convection flow and heat transfer; deep convolutional neural networks; deep learning


Steps to reproduce

The dataset is saved in two format, .npz for python and .mat for matlab. and ReadDataset_Matlab.m are examples of read data using python and matlab, respectively. For use dataset in matlab, download Dataset/NEPCM_Dataset_Matlab.mat, and then use ReadDataset_Matlab.m as an example. In case of python, download Dataset/NEPCM_Dataset.npz and run


Artificial Intelligence, Nanoparticles, Heat Transfer, Inverse Problem, Phase Change Material, Deep Neural Network, Natural Convection