Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network
The governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and e...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573323001195 |
| _version_ | 1827932957004791808 |
|---|---|
| author | Gibeom Kim Gyunyoung Heo |
| author_facet | Gibeom Kim Gyunyoung Heo |
| author_sort | Gibeom Kim |
| collection | DOAJ |
| description | The governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and enables rapid simulations, but it can be difficult to apply to situations with complex model parameters. Recently, a method of solving PDEs using artificial neural networks called physics-informed neural network (PINN) has been proposed. The PINN assumes the latent (hidden) solution of a PDE as an arbitrary neural network model and approximates the solution by optimizing the model. Unlike a Gaussian model, the PINN is intuitive in that it does not require special assumptions and uses the original equation without modifications. In this paper, we describe an approach to atmospheric dispersion modeling using the PINN and show its applicability through simple case studies. The results are compared with analytic and fundamental numerical methods to assess the accuracy and other features. The proposed PINN approximates the solution with reasonable accuracy. Considering that its procedure is divided into training and prediction steps, the PINN also offers the advantage of rapid simulations once the training is over. |
| first_indexed | 2024-03-13T07:17:50Z |
| format | Article |
| id | doaj.art-327de67df5aa43fc8974cdd97dfbd05c |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-03-13T07:17:50Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-327de67df5aa43fc8974cdd97dfbd05c2023-06-05T04:12:42ZengElsevierNuclear Engineering and Technology1738-57332023-06-0155623052314Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural networkGibeom Kim0Gyunyoung Heo1Department of Nuclear Engineering, Kyung Hee University, 1732 Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 17104, Republic of KoreaCorresponding author.; Department of Nuclear Engineering, Kyung Hee University, 1732 Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 17104, Republic of KoreaThe governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and enables rapid simulations, but it can be difficult to apply to situations with complex model parameters. Recently, a method of solving PDEs using artificial neural networks called physics-informed neural network (PINN) has been proposed. The PINN assumes the latent (hidden) solution of a PDE as an arbitrary neural network model and approximates the solution by optimizing the model. Unlike a Gaussian model, the PINN is intuitive in that it does not require special assumptions and uses the original equation without modifications. In this paper, we describe an approach to atmospheric dispersion modeling using the PINN and show its applicability through simple case studies. The results are compared with analytic and fundamental numerical methods to assess the accuracy and other features. The proposed PINN approximates the solution with reasonable accuracy. Considering that its procedure is divided into training and prediction steps, the PINN also offers the advantage of rapid simulations once the training is over.http://www.sciencedirect.com/science/article/pii/S1738573323001195Atmospheric dispersion modelingPhysics-informed neural network (PINN)Solutions of a partial differential equation |
| spellingShingle | Gibeom Kim Gyunyoung Heo Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network Nuclear Engineering and Technology Atmospheric dispersion modeling Physics-informed neural network (PINN) Solutions of a partial differential equation |
| title | Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network |
| title_full | Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network |
| title_fullStr | Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network |
| title_full_unstemmed | Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network |
| title_short | Solving partial differential equation for atmospheric dispersion of radioactive material using physics-informed neural network |
| title_sort | solving partial differential equation for atmospheric dispersion of radioactive material using physics informed neural network |
| topic | Atmospheric dispersion modeling Physics-informed neural network (PINN) Solutions of a partial differential equation |
| url | http://www.sciencedirect.com/science/article/pii/S1738573323001195 |
| work_keys_str_mv | AT gibeomkim solvingpartialdifferentialequationforatmosphericdispersionofradioactivematerialusingphysicsinformedneuralnetwork AT gyunyoungheo solvingpartialdifferentialequationforatmosphericdispersionofradioactivematerialusingphysicsinformedneuralnetwork |