Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method

Abstract The Fokker–Planck equation (FPE) has been used in many important applications to study stochastic processes with the evolution of the probability density function (pdf). Previous studies on FPE mainly focus on solving the forward problem which is to predict the time-evolution of the pdf fro...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wei Liu, Connie Khor Li Kou, Kun Hee Park, Hwee Kuan Lee
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/317ebbfd45d840cdabcb45e40112c67c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:317ebbfd45d840cdabcb45e40112c67c
record_format dspace
spelling oai:doaj.org-article:317ebbfd45d840cdabcb45e40112c67c2021-12-02T16:06:44ZSolving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method10.1038/s41598-021-94712-52045-2322https://doaj.org/article/317ebbfd45d840cdabcb45e40112c67c2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94712-5https://doaj.org/toc/2045-2322Abstract The Fokker–Planck equation (FPE) has been used in many important applications to study stochastic processes with the evolution of the probability density function (pdf). Previous studies on FPE mainly focus on solving the forward problem which is to predict the time-evolution of the pdf from the underlying FPE terms. However, in many applications the FPE terms are usually unknown and roughly estimated, and solving the forward problem becomes more challenging. In this work, we take a different approach of starting with the observed pdfs to recover the FPE terms using a self-supervised machine learning method. This approach, known as the inverse problem, has the advantage of requiring minimal assumptions on the FPE terms and allows data-driven scientific discovery of unknown FPE mechanisms. Specifically, we propose an FPE-based neural network (FPE-NN) which directly incorporates the FPE terms as neural network weights. By training the network on observed pdfs, we recover the FPE terms. Additionally, to account for noise in real-world observations, FPE-NN is able to denoise the observed pdfs by training the pdfs alongside the network weights. Our experimental results on various forms of FPE show that FPE-NN can accurately recover FPE terms and denoising the pdf plays an essential role.Wei LiuConnie Khor Li KouKun Hee ParkHwee Kuan LeeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Wei Liu
Connie Khor Li Kou
Kun Hee Park
Hwee Kuan Lee
Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
description Abstract The Fokker–Planck equation (FPE) has been used in many important applications to study stochastic processes with the evolution of the probability density function (pdf). Previous studies on FPE mainly focus on solving the forward problem which is to predict the time-evolution of the pdf from the underlying FPE terms. However, in many applications the FPE terms are usually unknown and roughly estimated, and solving the forward problem becomes more challenging. In this work, we take a different approach of starting with the observed pdfs to recover the FPE terms using a self-supervised machine learning method. This approach, known as the inverse problem, has the advantage of requiring minimal assumptions on the FPE terms and allows data-driven scientific discovery of unknown FPE mechanisms. Specifically, we propose an FPE-based neural network (FPE-NN) which directly incorporates the FPE terms as neural network weights. By training the network on observed pdfs, we recover the FPE terms. Additionally, to account for noise in real-world observations, FPE-NN is able to denoise the observed pdfs by training the pdfs alongside the network weights. Our experimental results on various forms of FPE show that FPE-NN can accurately recover FPE terms and denoising the pdf plays an essential role.
format article
author Wei Liu
Connie Khor Li Kou
Kun Hee Park
Hwee Kuan Lee
author_facet Wei Liu
Connie Khor Li Kou
Kun Hee Park
Hwee Kuan Lee
author_sort Wei Liu
title Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
title_short Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
title_full Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
title_fullStr Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
title_full_unstemmed Solving the inverse problem of time independent Fokker–Planck equation with a self supervised neural network method
title_sort solving the inverse problem of time independent fokker–planck equation with a self supervised neural network method
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/317ebbfd45d840cdabcb45e40112c67c
work_keys_str_mv AT weiliu solvingtheinverseproblemoftimeindependentfokkerplanckequationwithaselfsupervisedneuralnetworkmethod
AT conniekhorlikou solvingtheinverseproblemoftimeindependentfokkerplanckequationwithaselfsupervisedneuralnetworkmethod
AT kunheepark solvingtheinverseproblemoftimeindependentfokkerplanckequationwithaselfsupervisedneuralnetworkmethod
AT hweekuanlee solvingtheinverseproblemoftimeindependentfokkerplanckequationwithaselfsupervisedneuralnetworkmethod
_version_ 1718384895352373248