Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning
Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning
复制标题
DOI：
10.1175/bams-d-18-0195.1
复制
发表时间：
2019-11-01
影响因子：
8
通讯作者：
Smith, Travis
中科院分区：
文献类型：
--
作者：
McGovern, Amy;Lagerquist, Ryan;Smith, Travis
本文综合了机器学习（ML）模型解释和可视化（MIV）的多种方法，重点是气象应用。ML最近在包括气象学在内的许多领域都大受欢迎。虽然ML在气象学中取得了成功，但它并没有被广泛接受，主要是因为人们认为ML模型是“黑盒子”，这意味着ML方法被认为是输入并提供输出，但不能为用户提供物理上可解释的信息。本文介绍并演示了用于传统ML和深度学习的多种MIV技术，使气象学家能够了解ML模型学到了什么。我们讨论基于置换的预测的重要性，向前和向后选择，显着性图，类激活图，向后优化，和新奇检测。我们应用这些方法在多个时空尺度龙卷风，冰雹，冬季降水类型，对流风暴模式。通过分析如此广泛的应用，我们打算让这项工作揭开ML黑盒子的神秘面纱，提供应用MIV技术的见解，并作为气象学家和其他物理科学家的MIV工具箱。
This paper synthesizes multiple methods for machine learning (ML) model interpretation and visualization (MIV) focusing on meteorological applications. ML has recently exploded in popularity in many fields, including meteorology. Although ML has been successful in meteorology, it has not been as widely accepted, primarily due to the perception that ML models are "black boxes," meaning the ML methods are thought to take inputs and provide outputs but not to yield physically interpretable information to the user. This paper introduces and demonstrates multiple MIV techniques for both traditional ML and deep learning, to enable meteorologists to understand what ML models have learned. We discuss permutation-based predictor importance, forward and backward selection, saliency maps, class-activation maps, backward optimization, and novelty detection. We apply these methods at multiple spatiotemporal scales to tornado, hail, winter precipitation type, and convective-storm mode. By analyzing such a wide variety of applications, we intend for this work to demystify the black box of ML, offer insight in applying MIV techniques, and serve as a MIV toolbox for meteorologists and other physical scientists.