Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models
In the event of an accidental or intentional hazardous material release in the atmosphere, researchers often run physics-based atmospheric transport and dispersion models to predict the extent and variation of the contaminant spread. These predictions are imperfect due to propagated uncertainty from...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/8/953 |
| _version_ | 1797524682818191360 |
|---|---|
| author | Nipun Gunawardena Giuliana Pallotta Matthew Simpson Donald D. Lucas |
| author_facet | Nipun Gunawardena Giuliana Pallotta Matthew Simpson Donald D. Lucas |
| author_sort | Nipun Gunawardena |
| collection | DOAJ |
| description | In the event of an accidental or intentional hazardous material release in the atmosphere, researchers often run physics-based atmospheric transport and dispersion models to predict the extent and variation of the contaminant spread. These predictions are imperfect due to propagated uncertainty from atmospheric model physics (or parameterizations) and weather data initial conditions. Ensembles of simulations can be used to estimate uncertainty, but running large ensembles is often very time consuming and resource intensive, even using large supercomputers. In this paper, we present a machine-learning-based method which can be used to quickly emulate spatial deposition patterns from a multi-physics ensemble of dispersion simulations. We use a hybrid linear and logistic regression method that can predict deposition in more than 100,000 grid cells with as few as fifty training examples. Logistic regression provides probabilistic predictions of the presence or absence of hazardous materials, while linear regression predicts the quantity of hazardous materials. The coefficients of the linear regressions also open avenues of exploration regarding interpretability—the presented model can be used to find which physics schemes are most important over different spatial areas. A single regression prediction is on the order of 10,000 times faster than running a weather and dispersion simulation. However, considering the number of weather and dispersion simulations needed to train the regressions, the speed-up achieved when considering the whole ensemble is about 24 times. Ultimately, this work will allow atmospheric researchers to produce potential contamination scenarios with uncertainty estimates faster than previously possible, aiding public servants and first responders. |
| first_indexed | 2024-03-10T09:00:00Z |
| format | Article |
| id | doaj.art-07e7cfb012c34e99a48ebce5aa447a0b |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T09:00:00Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-07e7cfb012c34e99a48ebce5aa447a0b2023-11-22T06:46:54ZengMDPI AGAtmosphere2073-44332021-07-0112895310.3390/atmos12080953Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport ModelsNipun Gunawardena0Giuliana Pallotta1Matthew Simpson2Donald D. Lucas3Lawrence Livermore National Laboratory, Livermore, CA 94550, USALawrence Livermore National Laboratory, Livermore, CA 94550, USAScripps Institution of Oceanography, University of California San Diego, La Jolla, CA 92093, USALawrence Livermore National Laboratory, Livermore, CA 94550, USAIn the event of an accidental or intentional hazardous material release in the atmosphere, researchers often run physics-based atmospheric transport and dispersion models to predict the extent and variation of the contaminant spread. These predictions are imperfect due to propagated uncertainty from atmospheric model physics (or parameterizations) and weather data initial conditions. Ensembles of simulations can be used to estimate uncertainty, but running large ensembles is often very time consuming and resource intensive, even using large supercomputers. In this paper, we present a machine-learning-based method which can be used to quickly emulate spatial deposition patterns from a multi-physics ensemble of dispersion simulations. We use a hybrid linear and logistic regression method that can predict deposition in more than 100,000 grid cells with as few as fifty training examples. Logistic regression provides probabilistic predictions of the presence or absence of hazardous materials, while linear regression predicts the quantity of hazardous materials. The coefficients of the linear regressions also open avenues of exploration regarding interpretability—the presented model can be used to find which physics schemes are most important over different spatial areas. A single regression prediction is on the order of 10,000 times faster than running a weather and dispersion simulation. However, considering the number of weather and dispersion simulations needed to train the regressions, the speed-up achieved when considering the whole ensemble is about 24 times. Ultimately, this work will allow atmospheric researchers to produce potential contamination scenarios with uncertainty estimates faster than previously possible, aiding public servants and first responders.https://www.mdpi.com/2073-4433/12/8/953depositionmachine learninghazardous releaseWRFFLEXPARTprediction |
| spellingShingle | Nipun Gunawardena Giuliana Pallotta Matthew Simpson Donald D. Lucas Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models Atmosphere deposition machine learning hazardous release WRF FLEXPART prediction |
| title | Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models |
| title_full | Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models |
| title_fullStr | Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models |
| title_full_unstemmed | Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models |
| title_short | Machine Learning Emulation of Spatial Deposition from a Multi-Physics Ensemble of Weather and Atmospheric Transport Models |
| title_sort | machine learning emulation of spatial deposition from a multi physics ensemble of weather and atmospheric transport models |
| topic | deposition machine learning hazardous release WRF FLEXPART prediction |
| url | https://www.mdpi.com/2073-4433/12/8/953 |
| work_keys_str_mv | AT nipungunawardena machinelearningemulationofspatialdepositionfromamultiphysicsensembleofweatherandatmospherictransportmodels AT giulianapallotta machinelearningemulationofspatialdepositionfromamultiphysicsensembleofweatherandatmospherictransportmodels AT matthewsimpson machinelearningemulationofspatialdepositionfromamultiphysicsensembleofweatherandatmospherictransportmodels AT donalddlucas machinelearningemulationofspatialdepositionfromamultiphysicsensembleofweatherandatmospherictransportmodels |