Data-driven modeling of spatiotemporal physical processes with general deep
learning methods is a highly challenging task. It is further exacerbated by the
limited availability of data, leading to poor generalizations in standard
neural network models. To tackle this issue, we introduce a new approach called
the Finite Volume Neural Network (FINN). The FINN method adopts the numerical
structure of the well-known Finite Volume Method for handling partial
differential equations, so that each quantity of interest follows its own
adaptable conservation law, while it concurrently accommodates learnable
parameters. As a result, FINN enables better handling of fluxes between control
volumes and therefore proper treatment of different types of numerical boundary
conditions. We demonstrate the effectiveness of our approach with a subsurface
contaminant transport problem, which is governed by a non-linear
diffusion-sorption process. FINN does not only generalize better to differing
boundary conditions compared to other methods, it is also capable to explicitly
extract and learn the constitutive relationships (expressed by the retardation
factor). More importantly, FINN shows excellent generalization ability when
applied to both synthetic datasets and real, sparse experimental data, thus
underlining its relevance as a data-driven modeling tool.
Description
[2104.06010] Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
%0 Generic
%1 praditia2021finite
%A Praditia, Timothy
%A Karlbauer, Matthias
%A Otte, Sebastian
%A Oladyshkin, Sergey
%A Butz, Martin V.
%A Nowak, Wolfgang
%D 2021
%K deeplearning finn pde
%T Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
%U http://arxiv.org/abs/2104.06010
%X Data-driven modeling of spatiotemporal physical processes with general deep
learning methods is a highly challenging task. It is further exacerbated by the
limited availability of data, leading to poor generalizations in standard
neural network models. To tackle this issue, we introduce a new approach called
the Finite Volume Neural Network (FINN). The FINN method adopts the numerical
structure of the well-known Finite Volume Method for handling partial
differential equations, so that each quantity of interest follows its own
adaptable conservation law, while it concurrently accommodates learnable
parameters. As a result, FINN enables better handling of fluxes between control
volumes and therefore proper treatment of different types of numerical boundary
conditions. We demonstrate the effectiveness of our approach with a subsurface
contaminant transport problem, which is governed by a non-linear
diffusion-sorption process. FINN does not only generalize better to differing
boundary conditions compared to other methods, it is also capable to explicitly
extract and learn the constitutive relationships (expressed by the retardation
factor). More importantly, FINN shows excellent generalization ability when
applied to both synthetic datasets and real, sparse experimental data, thus
underlining its relevance as a data-driven modeling tool.
@misc{praditia2021finite,
abstract = {Data-driven modeling of spatiotemporal physical processes with general deep
learning methods is a highly challenging task. It is further exacerbated by the
limited availability of data, leading to poor generalizations in standard
neural network models. To tackle this issue, we introduce a new approach called
the Finite Volume Neural Network (FINN). The FINN method adopts the numerical
structure of the well-known Finite Volume Method for handling partial
differential equations, so that each quantity of interest follows its own
adaptable conservation law, while it concurrently accommodates learnable
parameters. As a result, FINN enables better handling of fluxes between control
volumes and therefore proper treatment of different types of numerical boundary
conditions. We demonstrate the effectiveness of our approach with a subsurface
contaminant transport problem, which is governed by a non-linear
diffusion-sorption process. FINN does not only generalize better to differing
boundary conditions compared to other methods, it is also capable to explicitly
extract and learn the constitutive relationships (expressed by the retardation
factor). More importantly, FINN shows excellent generalization ability when
applied to both synthetic datasets and real, sparse experimental data, thus
underlining its relevance as a data-driven modeling tool.},
added-at = {2021-09-10T08:14:53.000+0200},
author = {Praditia, Timothy and Karlbauer, Matthias and Otte, Sebastian and Oladyshkin, Sergey and Butz, Martin V. and Nowak, Wolfgang},
biburl = {https://www.bibsonomy.org/bibtex/2d06cc90f6bec99a698b2277c58e71041/annakrause},
description = {[2104.06010] Finite Volume Neural Network: Modeling Subsurface Contaminant Transport},
interhash = {36bd7d14f9c20909c2e5251713c8fa3d},
intrahash = {d06cc90f6bec99a698b2277c58e71041},
keywords = {deeplearning finn pde},
note = {cite arxiv:2104.06010Comment: Published as a workshop paper at ICLR 2021 SimDL Workshop},
timestamp = {2021-09-10T08:14:53.000+0200},
title = {Finite Volume Neural Network: Modeling Subsurface Contaminant Transport},
url = {http://arxiv.org/abs/2104.06010},
year = 2021
}