Learning <i>Effective Good</i> Variables from Physical Data

We assume that a sufficiently large database is available, where a physical property of interest and a number of associated ruling primitive variables or observables are stored. We introduce and test two machine learning approaches to discover possible groups or combinations of primitive variables,...

Full description

Saved in:
Bibliographic Details
Main Authors: Giulio Barletta, Giovanni Trezza, Eliodoro Chiavazzo
Format: Article
Language:English
Published: MDPI AG 2024-07-01
Series:Machine Learning and Knowledge Extraction
Subjects:
Online Access:https://www.mdpi.com/2504-4990/6/3/77
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260387563307008
author Giulio Barletta
Giovanni Trezza
Eliodoro Chiavazzo
author_facet Giulio Barletta
Giovanni Trezza
Eliodoro Chiavazzo
author_sort Giulio Barletta
collection DOAJ
description We assume that a sufficiently large database is available, where a physical property of interest and a number of associated ruling primitive variables or observables are stored. We introduce and test two machine learning approaches to discover possible groups or combinations of primitive variables, regardless of data origin, being it numerical or experimental: the first approach is based on regression models, whereas the second on classification models. The variable group (here referred to as the new effective good variable) can be considered as successfully found when the physical property of interest is characterized by the following effective invariant behavior: in the first method, invariance of the group implies invariance of the property up to a given accuracy; in the other method, upon partition of the physical property values into two or more classes, invariance of the group implies invariance of the class. For the sake of illustration, the two methods are successfully applied to two popular empirical correlations describing the convective heat transfer phenomenon and to the Newton’s law of universal gravitation.
format Article
id doaj-art-d981eb6008bc4d589cb2f0a76dd849fa
institution OA Journals
issn 2504-4990
language English
publishDate 2024-07-01
publisher MDPI AG
record_format Article
series Machine Learning and Knowledge Extraction
spelling doaj-art-d981eb6008bc4d589cb2f0a76dd849fa2025-08-20T01:55:38ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-07-01631597161810.3390/make6030077Learning <i>Effective Good</i> Variables from Physical DataGiulio Barletta0Giovanni Trezza1Eliodoro Chiavazzo2Department of Energy, Politecnico di Torino, C.so Duca degli Abruzzi 24, 10129 Torino, ItalyDepartment of Energy, Politecnico di Torino, C.so Duca degli Abruzzi 24, 10129 Torino, ItalyDepartment of Energy, Politecnico di Torino, C.so Duca degli Abruzzi 24, 10129 Torino, ItalyWe assume that a sufficiently large database is available, where a physical property of interest and a number of associated ruling primitive variables or observables are stored. We introduce and test two machine learning approaches to discover possible groups or combinations of primitive variables, regardless of data origin, being it numerical or experimental: the first approach is based on regression models, whereas the second on classification models. The variable group (here referred to as the new effective good variable) can be considered as successfully found when the physical property of interest is characterized by the following effective invariant behavior: in the first method, invariance of the group implies invariance of the property up to a given accuracy; in the other method, upon partition of the physical property values into two or more classes, invariance of the group implies invariance of the class. For the sake of illustration, the two methods are successfully applied to two popular empirical correlations describing the convective heat transfer phenomenon and to the Newton’s law of universal gravitation.https://www.mdpi.com/2504-4990/6/3/77machine learning in physicsprimitive variable analysisphysical property invariancefeature grouping
spellingShingle Giulio Barletta
Giovanni Trezza
Eliodoro Chiavazzo
Learning <i>Effective Good</i> Variables from Physical Data
Machine Learning and Knowledge Extraction
machine learning in physics
primitive variable analysis
physical property invariance
feature grouping
title Learning <i>Effective Good</i> Variables from Physical Data
title_full Learning <i>Effective Good</i> Variables from Physical Data
title_fullStr Learning <i>Effective Good</i> Variables from Physical Data
title_full_unstemmed Learning <i>Effective Good</i> Variables from Physical Data
title_short Learning <i>Effective Good</i> Variables from Physical Data
title_sort learning i effective good i variables from physical data
topic machine learning in physics
primitive variable analysis
physical property invariance
feature grouping
url https://www.mdpi.com/2504-4990/6/3/77
work_keys_str_mv AT giuliobarletta learningieffectivegoodivariablesfromphysicaldata
AT giovannitrezza learningieffectivegoodivariablesfromphysicaldata
AT eliodorochiavazzo learningieffectivegoodivariablesfromphysicaldata