paper-with-me

홈 › Papers

Solving differential equations with unknown constitutive relations as recurrent neural networks

2017-10-06 · Tobias Hagge, Panos Stinis, Enoch Yeung, Alexandre M. Tartakovsky

We solve a system of ordinary differential equations with an unknown functional form of a sink (reaction rate) term. We assume that the measurements (time series) of state variables are partially available, and we use recurrent neural network to "learn" the reaction rate from this data. This is achieved by including a discretized ordinary differential equations as part of a recurrent neural network training problem. We extend TensorFlow's recurrent neural network architecture to create a simple but scalable and effective solver for the unknown functions, and apply it to a fedbatch bioreactor simulation problem. Use of techniques from recent deep learning literature enables training of functions with behavior manifesting over thousands of time steps. Our networks are structurally similar to recurrent neural networks, but differences in design and function require modifications to the conventional wisdom about training such networks.

📄 PDF Abstract BibTeX arXiv:1710.02242

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Enhancing Multiscale Simulations with Constitutive Relations-Aware Deep Operator Networks

2024-05-22 · Hamidreza Eivazi, Mahyar Alikhani, Jendrik-Alexander Tröger, Stefan Wittek 외

Multiscale problems are widely observed across diverse domains in physics and engineering. Translating these problems into numerical simulations and solving them using numerical schemes, e.g. the finite element method, i…

A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations

2019-04-02 · Ramakrishna Tipireddy, Paris Perdikaris, Panos Stinis, Alexandre Tartakovsky

We investigate the use of discrete and continuous versions of physics-informed neural network methods for learning unknown dynamics or constitutive relations of a dynamical system. For the case of unknown dynamics, we re…

Physics-Informed Neural Networks for Dynamic Process Operations with Limited Physical Knowledge and Data

2024-06-03 · Mehmet Velioglu, Song Zhai, Sophia Rupprecht, Alexander Mitsos 외

In chemical engineering, process data are expensive to acquire, and complex phenomena are difficult to fully model. We explore the use of physics-informed neural networks (PINNs) for modeling dynamic processes with incom…

GIMLET: Generalizable and Interpretable Model Learning through Embedded Thermodynamics

2025-12-22 · Suguru Shiratori, Elham Kiyani, Khemraj Shukla, George Em Karniadakis arxiv

We develop a data-driven framework for discovering constitutive relations in models of fluid flow and scalar transport. Under the assumption that velocity and/or scalar fields are measured, our approach infers unknown cl…

Solving high-dimensional partial differential equations using deep learning

2017-07-09 · Jiequn Han, Arnulf Jentzen, Weinan E

Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the "curse of dimensional…

Deep LearningDeep Reinforcement LearningReinforcement LearningVocal Bursts Intensity Prediction