Evaluation, Tuning, and Interpretation of Neural Networks for Working with Images in Meteorological Applications
Evaluation, Tuning, and Interpretation of Neural Networks for Working with Images in Meteorological Applications
复制标题
DOI：
10.1175/bams-d-20-0097.1
复制
发表时间：
2020-12-01
影响因子：
8
通讯作者：
Hilburn, Kyle
中科院分区：
文献类型：
--
作者：
Ebert-Uphoff, Imme;Hilburn, Kyle
神经网络方法(又名深度学习)为在气象学中利用遥感图像开辟了许多新的机会。常见的应用包括图像分类，例如确定图像是否包含热带气旋，以及图像到图像的转换，例如为只有被动通道的卫星模拟雷达图像。然而，关于使用神经网络处理气象图像，仍有许多悬而未决的问题，如评估、调整和解释的最佳做法。本文重点介绍了几种尚未受到气象界重视的神经网络发展策略和实际考虑，如接受场的概念、未得到充分利用的气象性能指标以及神经网络解释的方法，如合成实验和分层相关传播。我们还将神经网络解释过程作为一个整体来考虑，认为它是一个迭代的气象学家驱动的发现过程，建立在实验设计和假设生成和测试的基础上。最后，虽然到目前为止，气象学中关于神经网络解释的大部分工作都集中在用于图像分类任务的网络上，但我们将重点扩大到也包括用于图像到图像转换的网络。
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.