skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning
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.  more » « less
Award ID(s):
1802627
PAR ID:
10132736
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Bulletin of the American Meteorological Society
Volume:
100
Issue:
11
ISSN:
0003-0007
Page Range / eLocation ID:
2175 to 2199
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Weather and Forecasting)
    Abstract Recently, the use of machine learning in meteorology has increased greatly. While many machine learning methods are not new, university classes on machine learning are largely unavailable to meteorology students and are not required to become a meteorologist. The lack of formal instruction has contributed to perception that machine learning methods are “black boxes” and thus end-users are hesitant to apply the machine learning methods in their everyday workflow. To reduce the opaqueness of machine learning methods and lower hesitancy toward machine learning in meteorology, this paper provides a survey of some of the most common machine learning methods. A familiar meteorological example is used to contextualize the machine learning methods while also discussing machine learning topics using plain language. The following machine learning methods are demonstrated: linear regression, logistic regression, decision trees, random forest, gradient boosted decision trees, naïve Bayes, and support vector machines. Beyond discussing the different methods, the paper also contains discussions on the general machine learning process as well as best practices to enable readers to apply machine learning to their own datasets. Furthermore, all code (in the form of Jupyter notebooks and Google Colaboratory notebooks) used to make the examples in the paper is provided in an effort to catalyze the use of machine learning in meteorology. 
    more » « less
  2. ; ; ; (, Weather and Forecasting)
    Abstract Over the past decade the use of machine learning in meteorology has grown rapidly. Specifically neural networks and deep learning have been used at an unprecedented rate. To fill the dearth of resources covering neural networks with a meteorological lens, this paper discusses machine learning methods in a plain language format that is targeted to the operational meteorological community. This is the second paper in a pair that aim to serve as a machine learning resource for meteorologists. While the first paper focused on traditional machine learning methods (e.g., random forest), here a broad spectrum of neural networks and deep learning methods is discussed. Specifically, this paper covers perceptrons, artificial neural networks, convolutional neural networks, and U-networks. Like the Part I paper, this manuscript discusses the terms associated with neural networks and their training. Then the manuscript provides some intuition behind every method and concludes by showing each method used in a meteorological example of diagnosing thunderstorms from satellite images (e.g., lightning flashes). This paper is accompanied with an open-source code repository to allow readers to explore neural networks using either the dataset provided (which is used in the paper) or as a template for alternate datasets. 
    more » « less
  3. (, Journal of manufacturing systems)
    Machine learning (ML) has shown to be an effective alternative to physical models for quality prediction and process optimization of metal additive manufacturing (AM). However, the inherent “black box” nature of ML techniques such as those represented by artificial neural networks has often presented a challenge to interpret ML outcomes in the framework of the complex thermodynamics that govern AM. While the practical benefits of ML provide an adequate justification, its utility as a reliable modeling tool is ultimately reliant on assured consistency with physical principles and model transparency. To facilitate the fundamental needs, physics-informed machine learning (PIML) has emerged as a hybrid machine learning paradigm that imbues ML models with physical domain knowledge such as thermomechanical laws and constraints. The distinguishing feature of PIML is the synergistic integration of data-driven methods that reflect system dynamics in real-time with the governing physics underlying AM. In this paper, the current state-of-the-art in metal AM is reviewed and opportunities for a paradigm shift to PIML are discussed, thereby identifying relevant future research directions. 
    more » « less
  4. ; ; ; (, Process Safety and Environmental Protection)
    Chen, Guohua; Khan, Faisal (Ed.)
    Artificial intelligence (AI) and machine learning (ML) are novel techniques to detect hidden patterns in environmental data. Despite their capabilities, these novel technologies have not been seriously used for real-world problems, such as real-time environmental monitoring. This survey established a framework to advance the novel applications of AI and ML techniques such as Tiny Machine Learning (TinyML) in water environments. The survey covered deep learning models and their advantages over classical ML models. The deep learning algorithms are the heart of TinyML models and are of paramount importance for practical uses in water environments. This survey highlighted the capabilities and discussed the possible applications of the TinyML models in water environments. This study indicated that the TinyML models on microcontrollers are useful for a number of cutting-edge problems in water environments, especially for monitoring purposes. The TinyML models on microcontrollers allow for in situ real-time environmental monitoring without transferring data to the cloud. It is concluded that monitoring systems based on TinyML models offer cheap tools to autonomously track pollutants in water and can replace traditional monitoring methods. 
    more » « less
  5. ; ; ; ; ; (, ACM Conference on Computer and Communications Security (CCS))
    Several recent research efforts have proposed Machine Learning (ML)-based solutions that can detect complex patterns in network traffic for a wide range of network security problems. However, without understanding how these black-box models are making their decisions, network operators are reluctant to trust and deploy them in their production settings. One key reason for this reluctance is that these models are prone to the problem of underspecification, defined here as the failure to specify a model in adequate detail. Not unique to the network security domain, this problem manifests itself in ML models that exhibit unexpectedly poor behavior when deployed in real-world settings and has prompted growing interest in developing interpretable ML solutions (e.g., decision trees) for “explaining” to humans how a given black-box model makes its decisions. However, synthesizing such explainable models that capture a given black-box model’s decisions with high fidelity while also being practical (i.e., small enough in size for humans to comprehend) is challenging. In this paper, we focus on synthesizing high-fidelity and low-complexity decision trees to help network operators determine if their ML models suffer from the problem of underspecification. To this end, we present TRUSTEE, a framework that takes an existing ML model and training dataset generate a high-fidelity, easy-to-interpret decision tree, and associated trust report. Using published ML models that are fully reproducible, we show how practitioners can use TRUSTEE to identify three common instances of model underspecification, i.e., evidence of shortcut learning, spurious correlations, and vulnerability to out-of-distribution samples. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email