UniFIDES: Universal fractional integro-differential equations solver

The development of data-driven approaches for solving differential equations has led to numerous applications in science and engineering across many disciplines and remains a central focus of active scientific inquiry. However, a large body of natural phenomena incorporates memory effects that are b...

Full description

Saved in:
Bibliographic Details
Main Authors: Milad Saadat, Deepak Mangal, Safa Jamali
Format: Article
Language:English
Published: AIP Publishing LLC 2025-03-01
Series:APL Machine Learning
Online Access:http://dx.doi.org/10.1063/5.0258122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766890910515200
author Milad Saadat
Deepak Mangal
Safa Jamali
author_facet Milad Saadat
Deepak Mangal
Safa Jamali
author_sort Milad Saadat
collection DOAJ
description The development of data-driven approaches for solving differential equations has led to numerous applications in science and engineering across many disciplines and remains a central focus of active scientific inquiry. However, a large body of natural phenomena incorporates memory effects that are best described via fractional integro-differential equations (FIDEs), in which the integral or differential operators accept non-integer orders. Addressing the challenges posed by nonlinear FIDEs is a recognized difficulty, necessitating the application of generic methods with immediate practical relevance. This work introduces the Universal Fractional Integro-Differential Equations Solver (UniFIDES), a comprehensive machine learning platform designed to expeditiously solve a variety of FIDEs in both forward and inverse directions, without the need for ad hoc manipulation of the equations. The effectiveness of UniFIDES is demonstrated through a collection of integer-order and fractional problems in science and engineering. Our results highlight UniFIDES’ ability to accurately solve a wide spectrum of integro-differential equations and offer the prospect of using machine learning platforms universally for discovering and describing dynamic and complex systems.
format Article
id doaj-art-5db19103d7e24482a3ee7d05a0637a5f
institution DOAJ
issn 2770-9019
language English
publishDate 2025-03-01
publisher AIP Publishing LLC
record_format Article
series APL Machine Learning
spelling doaj-art-5db19103d7e24482a3ee7d05a0637a5f2025-08-20T03:04:26ZengAIP Publishing LLCAPL Machine Learning2770-90192025-03-0131016116016116-1110.1063/5.0258122UniFIDES: Universal fractional integro-differential equations solverMilad Saadat0Deepak Mangal1Safa Jamali2Department of Mechanical and Industrial Engineering, Northeastern University, Boston, Massachusetts 02115, USADepartment of Mechanical and Industrial Engineering, Northeastern University, Boston, Massachusetts 02115, USADepartment of Mechanical and Industrial Engineering, Northeastern University, Boston, Massachusetts 02115, USAThe development of data-driven approaches for solving differential equations has led to numerous applications in science and engineering across many disciplines and remains a central focus of active scientific inquiry. However, a large body of natural phenomena incorporates memory effects that are best described via fractional integro-differential equations (FIDEs), in which the integral or differential operators accept non-integer orders. Addressing the challenges posed by nonlinear FIDEs is a recognized difficulty, necessitating the application of generic methods with immediate practical relevance. This work introduces the Universal Fractional Integro-Differential Equations Solver (UniFIDES), a comprehensive machine learning platform designed to expeditiously solve a variety of FIDEs in both forward and inverse directions, without the need for ad hoc manipulation of the equations. The effectiveness of UniFIDES is demonstrated through a collection of integer-order and fractional problems in science and engineering. Our results highlight UniFIDES’ ability to accurately solve a wide spectrum of integro-differential equations and offer the prospect of using machine learning platforms universally for discovering and describing dynamic and complex systems.http://dx.doi.org/10.1063/5.0258122
spellingShingle Milad Saadat
Deepak Mangal
Safa Jamali
UniFIDES: Universal fractional integro-differential equations solver
APL Machine Learning
title UniFIDES: Universal fractional integro-differential equations solver
title_full UniFIDES: Universal fractional integro-differential equations solver
title_fullStr UniFIDES: Universal fractional integro-differential equations solver
title_full_unstemmed UniFIDES: Universal fractional integro-differential equations solver
title_short UniFIDES: Universal fractional integro-differential equations solver
title_sort unifides universal fractional integro differential equations solver
url http://dx.doi.org/10.1063/5.0258122
work_keys_str_mv AT miladsaadat unifidesuniversalfractionalintegrodifferentialequationssolver
AT deepakmangal unifidesuniversalfractionalintegrodifferentialequationssolver
AT safajamali unifidesuniversalfractionalintegrodifferentialequationssolver