Introduction to machine learning in undergraduate physics.
Saved in:
| Title: | Introduction to machine learning in undergraduate physics. |
|---|---|
| Authors: | Mubin, Shafat1 (AUTHOR) smubin@valdosta.edu, Wellons, Xavier1 (AUTHOR) xswellons@valdosta.edu |
| Source: | American Journal of Physics. Mar2026, Vol. 94 Issue 3, p217-223. 7p. |
| Subjects: | Machine learning, Mathematica (Computer software), Simulation methods & models, Kinematics, Projectiles, Thermodynamics, Physics education |
| Abstract: | We provide an introduction to machine learning methods that can be applied to concepts covered in undergraduate physics, such as projectile motion and experimental force measurements. User-friendly features in Mathematica allow datasets, for instance representing trajectories and microstate configurations, to train the machine learning models, which are then used to predict kinematics parameters or thermodynamic configurations of new input sets. The datasets consist of numerical values and images, which are utilized in the training model with minimal coding. The short and straightforward Mathematica codes, compared to other mainstream programming languages, make the process accessible to users who do not possess extensive programming experience. Editor's Note: You know AI and Machine Learning are important topics to teach your students, but you don't really know how to introduce these tools in your undergraduate physics curriculum? This paper provides you with a few examples, taken from the fields of mechanics and thermodynamics and requiring minimal programming expertise. Using Mathematica's built-in machine learning models, the authors demonstrate how these can be trained on numerical datasets, simulated trajectories, and even pictures to extract physical parameters. For instance, given the 2D trajectory of a projectile, a trained model is able to determine its drag coefficient. These examples illustrate how machine learning can (almost painlessly) be integrated into existing courses, providing students with hands-on experience in modern computational methods while deepening their physics understanding. [ABSTRACT FROM AUTHOR] |
| Copyright of American Journal of Physics is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191768126 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Introduction to machine learning in undergraduate physics. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Mubin%2C+Shafat%22">Mubin, Shafat</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> smubin@valdosta.edu</i><br /><searchLink fieldCode="AR" term="%22Wellons%2C+Xavier%22">Wellons, Xavier</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> xswellons@valdosta.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22American+Journal+of+Physics%22">American Journal of Physics</searchLink>. Mar2026, Vol. 94 Issue 3, p217-223. 7p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematica+%28Computer+software%29%22">Mathematica (Computer software)</searchLink><br /><searchLink fieldCode="DE" term="%22Simulation+methods+%26+models%22">Simulation methods & models</searchLink><br /><searchLink fieldCode="DE" term="%22Kinematics%22">Kinematics</searchLink><br /><searchLink fieldCode="DE" term="%22Projectiles%22">Projectiles</searchLink><br /><searchLink fieldCode="DE" term="%22Thermodynamics%22">Thermodynamics</searchLink><br /><searchLink fieldCode="DE" term="%22Physics+education%22">Physics education</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We provide an introduction to machine learning methods that can be applied to concepts covered in undergraduate physics, such as projectile motion and experimental force measurements. User-friendly features in Mathematica allow datasets, for instance representing trajectories and microstate configurations, to train the machine learning models, which are then used to predict kinematics parameters or thermodynamic configurations of new input sets. The datasets consist of numerical values and images, which are utilized in the training model with minimal coding. The short and straightforward Mathematica codes, compared to other mainstream programming languages, make the process accessible to users who do not possess extensive programming experience. Editor's Note: You know AI and Machine Learning are important topics to teach your students, but you don't really know how to introduce these tools in your undergraduate physics curriculum? This paper provides you with a few examples, taken from the fields of mechanics and thermodynamics and requiring minimal programming expertise. Using Mathematica's built-in machine learning models, the authors demonstrate how these can be trained on numerical datasets, simulated trajectories, and even pictures to extract physical parameters. For instance, given the 2D trajectory of a projectile, a trained model is able to determine its drag coefficient. These examples illustrate how machine learning can (almost painlessly) be integrated into existing courses, providing students with hands-on experience in modern computational methods while deepening their physics understanding. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of American Journal of Physics is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191768126 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1119/5.0243715 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 7 StartPage: 217 Subjects: – SubjectFull: Machine learning Type: general – SubjectFull: Mathematica (Computer software) Type: general – SubjectFull: Simulation methods & models Type: general – SubjectFull: Kinematics Type: general – SubjectFull: Projectiles Type: general – SubjectFull: Thermodynamics Type: general – SubjectFull: Physics education Type: general Titles: – TitleFull: Introduction to machine learning in undergraduate physics. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Mubin, Shafat – PersonEntity: Name: NameFull: Wellons, Xavier IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 00029505 Numbering: – Type: volume Value: 94 – Type: issue Value: 3 Titles: – TitleFull: American Journal of Physics Type: main |
| ResultId | 1 |
