气候变化领域集成服务门户(CCPortal): Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications

CCPortal

DOI	10.1175/BAMS-D-20-0097.1
	Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications
	Ebert-Uphoff I.; Hilburn K.
发表日期	2020
ISSN	00030007
起始页码	E2149
结束页码	E2170
卷号	101 期号:12
英文摘要	The method of neural networks (aka deep learning) has opened up many new opportunities to utilize remotely sensed images in meteorology. Common applications include image classification, e.g., to determine whether an image contains a tropical cyclone, and image-to-image translation, e.g., to emulate radar imagery for satellites that only have passive channels. However, there are yet many open questions regarding the use of neural networks for working with meteorological images, such as best practices for evaluation, tuning, and interpretation. This article highlights several strategies and practical considerations for neural network development that have not yet received much attention in the meteorological community, such as the concept of receptive fields, underutilized meteorological performance measures, and methods for neural network interpretation, such as synthetic experiments and layer-wise relevance propagation. We also consider the process of neural network interpretation as a whole, recognizing it as an iterative meteorologist-driven discovery process that builds on experimental design and hypothesis generation and testing. Finally, while most work on neural network interpretation in meteorology has so far focused on networks for image classification tasks, we expand the focus to also include networks for image-to-image translation. ©2020 American Meteorological Society.
英文关键词	Artificial intelligence; Deep learning; Machine learning; Neural networks; Radars/radar observations; Satellite observations
语种	英语
scopus关键词	Backpropagation; Deep learning; Image classification; Iterative methods; Radar imaging; Storms; Tracking radar; Hypothesis generation; Image translation; Network development; Performance measure; Receptive fields; Remotely sensed images; Synthetic experiments; Tropical cyclone; Multilayer neural networks
来源期刊	Bulletin of the American Meteorological Society
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/177786
作者单位	Electrical and Computer Engineering, and Cooperative Institute for Research in the Atmosphere, Colorado State University, Fort Collins, CO, United States; Cooperative Institute for Research in Atmosphere, Colorado State University, Fort Collins, CO, United States
推荐引用方式 GB/T 7714	Ebert-Uphoff I.,Hilburn K.. Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications[J],2020,101(12).
APA	Ebert-Uphoff I.,&Hilburn K..(2020).Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications.Bulletin of the American Meteorological Society,101(12).
MLA	Ebert-Uphoff I.,et al."Evaluation, tuning, and interpretation of neural networks for working with images in meteorological applications".Bulletin of the American Meteorological Society 101.12(2020).