An enhanced fourier neural operator surrogate for radioactive plume transport forecasting
Accurate real-time forecasts of atmospheric plume behavior are crucial for effective management of environmental release incidents. However, the computational demands of weather simulations and particle transport codes limit their applicability during emergencies. In this study, we employ a U-Net en...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2024
|
| Online Access: | https://hdl.handle.net/1721.1/154998 |
| _version_ | 1826216429495517184 |
|---|---|
| author | Ayoub, Ali Wainwright, Haruko M. Wang, Lijing Sansavini, Giovanni |
| author2 | Massachusetts Institute of Technology. Department of Nuclear Science and Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Nuclear Science and Engineering Ayoub, Ali Wainwright, Haruko M. Wang, Lijing Sansavini, Giovanni |
| author_sort | Ayoub, Ali |
| collection | MIT |
| description | Accurate real-time forecasts of atmospheric plume behavior are crucial for effective management of environmental release incidents. However, the computational demands of weather simulations and particle transport codes limit their applicability during emergencies. In this study, we employ a U-Net enhanced Fourier Neural Operator (U-FNO) to statistically emulate the calculations of the WSPEEDI dose forecasting numerical simulator, using pre-calculated ensemble simulations. The developed emulator is capable of effectively simulating any radioactive-release scenario and generating the time series of dose distribution in the environment 4000 times faster than the numerical simulator, while still maintaining high accuracy. It predicts the plume direction, extent, and dose-rate magnitudes using initial- and boundary-condition meteorological data as input. The speed and efficiency of this framework offers a powerful tool for swift decision-making during emergencies, facilitating risk-informed protective actions, evacuation execution, and zone delineation. Its application extends to various contaminant release and transport problems, and can be instrumental in engineering tasks requiring uncertainty quantification (UQ) for environmental risk assessment. |
| first_indexed | 2024-09-23T16:47:32Z |
| format | Article |
| id | mit-1721.1/154998 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:25:59Z |
| publishDate | 2024 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1549982025-01-01T04:23:46Z An enhanced fourier neural operator surrogate for radioactive plume transport forecasting Ayoub, Ali Wainwright, Haruko M. Wang, Lijing Sansavini, Giovanni Massachusetts Institute of Technology. Department of Nuclear Science and Engineering Accurate real-time forecasts of atmospheric plume behavior are crucial for effective management of environmental release incidents. However, the computational demands of weather simulations and particle transport codes limit their applicability during emergencies. In this study, we employ a U-Net enhanced Fourier Neural Operator (U-FNO) to statistically emulate the calculations of the WSPEEDI dose forecasting numerical simulator, using pre-calculated ensemble simulations. The developed emulator is capable of effectively simulating any radioactive-release scenario and generating the time series of dose distribution in the environment 4000 times faster than the numerical simulator, while still maintaining high accuracy. It predicts the plume direction, extent, and dose-rate magnitudes using initial- and boundary-condition meteorological data as input. The speed and efficiency of this framework offers a powerful tool for swift decision-making during emergencies, facilitating risk-informed protective actions, evacuation execution, and zone delineation. Its application extends to various contaminant release and transport problems, and can be instrumental in engineering tasks requiring uncertainty quantification (UQ) for environmental risk assessment. 2024-05-20T14:30:42Z 2024-05-20T14:30:42Z 2024-05-16 2024-05-19T03:12:57Z Article http://purl.org/eprint/type/JournalArticle 1436-3240 1436-3259 https://hdl.handle.net/1721.1/154998 Ayoub, A., Wainwright, H.M., Wang, L. et al. An enhanced fourier neural operator surrogate for radioactive plume transport forecasting. Stoch Environ Res Risk Assess (2024). PUBLISHER_CC en 10.1007/s00477-024-02738-8 Stochastic Environmental Research and Risk Assessment Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Science and Business Media LLC Springer Berlin Heidelberg |
| spellingShingle | Ayoub, Ali Wainwright, Haruko M. Wang, Lijing Sansavini, Giovanni An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title | An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title_full | An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title_fullStr | An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title_full_unstemmed | An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title_short | An enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| title_sort | enhanced fourier neural operator surrogate for radioactive plume transport forecasting |
| url | https://hdl.handle.net/1721.1/154998 |
| work_keys_str_mv | AT ayoubali anenhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT wainwrightharukom anenhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT wanglijing anenhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT sansavinigiovanni anenhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT ayoubali enhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT wainwrightharukom enhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT wanglijing enhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting AT sansavinigiovanni enhancedfourierneuraloperatorsurrogateforradioactiveplumetransportforecasting |