There is a newer version of the record available.

Published June 13, 2024 | Version v2
Preprint Open

Models and datasets for "Learning effective good variables from physical data"

  • 1. Politecnico di Torino

Description

Trained models and datasets related to the GitHub repository https://github.com/giuliobarl/GoodPhysVariables and to our publication 

  • Dittus.xlsx, Gnielinski.xlsx, and Newton.xlsx are the original datasets with no noise;
  • Dittus Noise.xlsx, Gnielinski Noise.xlsx, and Newton Noise.xlsx are the datasets to which gaussian noise has been added, and that are used to train the DNN models;
  • dittus_model.tf.zip contains the trained DNN model for the Dittus-Boelter correlation;
  • gnielinski_model.tf.zip contains the trained DNN model for the Gnielinski correlation;
  • newton_model.tf.zip contains the trained DNN model for Newton's law of universal gravitation.

Files

dittus_model.tf.zip

Files (637.5 kB)

Name Size Download all
md5:eec50b6bb4c295c88538e59adaaa351e
200.4 kB Preview Download
md5:3410be7b291d7434afbe91e8d7083b3b
212.7 kB Preview Download
md5:edaaacc217e224d8647454b752672490
224.4 kB Preview Download