Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915464140029952 |
|---|---|
| author | Sun, Yixuan Egele, Romain Narayanan, Sri Hari Krishna Van Roekel, Luke Gonzales, Carmelo Brus, Steven Nadiga, Balu Madireddy, Sandeep Balaprakash, Prasanna |
| author_facet | Sun, Yixuan Egele, Romain Narayanan, Sri Hari Krishna Van Roekel, Luke Gonzales, Carmelo Brus, Steven Nadiga, Balu Madireddy, Sandeep Balaprakash, Prasanna |
| contents | Accurate simulations of the oceans are crucial in understanding the Earth system. Despite their efficiency, simulations at lower resolutions must rely on various uncertain parameterizations to account for unresolved processes. However, model sensitivity to parameterizations is difficult to quantify, making it challenging to tune these parameterizations to reproduce observations. Deep learning surrogates have shown promise for efficient computation of the parametric sensitivities in the form of partial derivatives, but their reliability is difficult to evaluate without ground truth derivatives. In this work, we leverage large-scale hyperparameter search and ensemble learning to improve both forward predictions, autoregressive rollout, and backward adjoint sensitivity estimation. Particularly, the ensemble method provides epistemic uncertainty of function value predictions and their derivatives, providing improved reliability of the neural surrogates in decision making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16489 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling Sun, Yixuan Egele, Romain Narayanan, Sri Hari Krishna Van Roekel, Luke Gonzales, Carmelo Brus, Steven Nadiga, Balu Madireddy, Sandeep Balaprakash, Prasanna Atmospheric and Oceanic Physics Machine Learning Accurate simulations of the oceans are crucial in understanding the Earth system. Despite their efficiency, simulations at lower resolutions must rely on various uncertain parameterizations to account for unresolved processes. However, model sensitivity to parameterizations is difficult to quantify, making it challenging to tune these parameterizations to reproduce observations. Deep learning surrogates have shown promise for efficient computation of the parametric sensitivities in the form of partial derivatives, but their reliability is difficult to evaluate without ground truth derivatives. In this work, we leverage large-scale hyperparameter search and ensemble learning to improve both forward predictions, autoregressive rollout, and backward adjoint sensitivity estimation. Particularly, the ensemble method provides epistemic uncertainty of function value predictions and their derivatives, providing improved reliability of the neural surrogates in decision making. |
| title | Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2508.16489 |