气候变化领域集成服务门户(CCPortal): The graft-versus-host problem for data-driven gravity-wave parameterizations in a one-dimensional quasibiennial oscillation model

CCPortal

DOI	10.1002/qj.4707
	The graft-versus-host problem for data-driven gravity-wave parameterizations in a one-dimensional quasibiennial oscillation model
发表日期	2024
ISSN	0035-9009
EISSN	1477-870X
起始页码	150
结束页码	761
卷号	150 期号:761
英文摘要	Two key challenges in the development of data-driven gravity-wave parameterizations are generalization, how to ensure that a data-driven scheme trained on the present-day climate will continue to work in a new climate regime, and calibration, how to account for biases in the host climate model. Both problems depend fundamentally on the response to out-of-sample inputs compared with the training dataset, and are often conflicting. The ability to generalize to new climate regimes often goes hand in hand with sensitivity to model biases. To probe these challenges, we employ a one-dimensional (1D) quasibiennial oscillation (QBO) model with a stochastic source term that represents convectively generated gravity waves in the Tropics with randomly varying strengths and spectra. We employ an array of machine-learning models consisting of a fully connected feed-forward neural network, a dilated convolutional neural network, an encoder-decoder, a boosted forest, and a support-vector regression model. Our results demonstrate that data-driven schemes trained on observations can be critically sensitive to model biases in the wave sources. While able to emulate accurately the stochastic source term on which they were trained, all of our schemes fail to simulate fully the expected QBO period or amplitude, even with the slightest perturbation to the wave sources. The main takeaway is that some measures will always be required to ensure the proper response to climate change and to account for model biases. We examine one approach based on the ideas of optimal transport, where the wave sources in the model are first remapped to the observed one before applying the data-driven scheme. This approach is agnostic to the data-driven method and guarantees that the model adheres to the observational constraints, making sure the model yields the right results for the right reasons. Data-driven models can emulate the gravity-wave drags in a one-dimensional quasibiennial oscillation model on which they were trained accurately, yielding the correct winds when coupled back to the one-dimensional model. However, they are sensitive to perturbations in the gravity-wave sources, for example, due to climate model biases or climate change. An effective solution for model biases is to remap the wave sources before feeding them to the data-driven methods. However, the response to climate change is an ongoing challenge. image
英文关键词	data-driven; gravity waves; machine learning; quasibiennial oscillation; subgrid-scale parameterizations
语种	英语
WOS研究方向	Meteorology & Atmospheric Sciences
WOS类目	Meteorology & Atmospheric Sciences
WOS记录号	WOS:001190682400001
来源期刊	QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/288569
作者单位	New York University; Met Office - UK; Hadley Centre; New York University; University of California System; University of California San Diego
推荐引用方式 GB/T 7714	. The graft-versus-host problem for data-driven gravity-wave parameterizations in a one-dimensional quasibiennial oscillation model[J],2024,150(761).
APA	(2024).The graft-versus-host problem for data-driven gravity-wave parameterizations in a one-dimensional quasibiennial oscillation model.QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY,150(761).
MLA	"The graft-versus-host problem for data-driven gravity-wave parameterizations in a one-dimensional quasibiennial oscillation model".QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY 150.761(2024).

条目包含的文件
条目无相关文件。

个性服务

谷歌学术

百度学术

必应学术

相关权益政策

收藏/分享