Explainable Offline-Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave-QBO Testbed in the Small-data Regime

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pahlavan, Hamid A., Hassanzadeh, Pedram, Alexander, M. Joan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917722481229824
author Pahlavan, Hamid A.
Hassanzadeh, Pedram
Alexander, M. Joan
author_facet Pahlavan, Hamid A.
Hassanzadeh, Pedram
Alexander, M. Joan
contents There are different strategies for training neural networks (NNs) as subgrid-scale parameterizations. Here, we use a 1D model of the quasi-biennial oscillation (QBO) and gravity wave (GW) parameterizations as testbeds. A 12-layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in a big-data regime (100-years), produces realistic QBOs once coupled to the 1D model. In contrast, offline training of this NN in a small-data regime (18-months) yields unrealistic QBOs. However, online re-training of just two layers of this NN using ensemble Kalman inversion and only time-averaged QBO statistics leads to parameterizations that yield realistic QBOs. Fourier analysis of these three NNs' kernels suggests why/how re-training works and reveals that these NNs primarily learn low-pass, high-pass, and a combination of band-pass filters, consistent with the importance of both local and non-local dynamics in GW propagation/dissipation. These findings/strategies apply to data-driven parameterizations of other climate processes generally.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09024
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Explainable Offline-Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave-QBO Testbed in the Small-data Regime
Pahlavan, Hamid A.
Hassanzadeh, Pedram
Alexander, M. Joan
Atmospheric and Oceanic Physics
Computational Physics
Data Analysis, Statistics and Probability
There are different strategies for training neural networks (NNs) as subgrid-scale parameterizations. Here, we use a 1D model of the quasi-biennial oscillation (QBO) and gravity wave (GW) parameterizations as testbeds. A 12-layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in a big-data regime (100-years), produces realistic QBOs once coupled to the 1D model. In contrast, offline training of this NN in a small-data regime (18-months) yields unrealistic QBOs. However, online re-training of just two layers of this NN using ensemble Kalman inversion and only time-averaged QBO statistics leads to parameterizations that yield realistic QBOs. Fourier analysis of these three NNs' kernels suggests why/how re-training works and reveals that these NNs primarily learn low-pass, high-pass, and a combination of band-pass filters, consistent with the importance of both local and non-local dynamics in GW propagation/dissipation. These findings/strategies apply to data-driven parameterizations of other climate processes generally.
title Explainable Offline-Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave-QBO Testbed in the Small-data Regime
topic Atmospheric and Oceanic Physics
Computational Physics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2309.09024