Explainable Machine Learning for Scientific Insights and Discoveries
Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scient...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9007737/ |
id |
doaj-07abd4e1023e4666a93531d3bcbd6d7f |
---|---|
record_format |
Article |
spelling |
doaj-07abd4e1023e4666a93531d3bcbd6d7f2021-03-30T02:07:06ZengIEEEIEEE Access2169-35362020-01-018422004221610.1109/ACCESS.2020.29761999007737Explainable Machine Learning for Scientific Insights and DiscoveriesRibana Roscher0Bastian Bohn1Marco F. Duarte2Jochen Garcke3https://orcid.org/0000-0002-8334-3695Institute of Geodesy and Geoinformation, University of Bonn, Bonn, GermanyInstitute for Numerical Simulation, University of Bonn, Bonn, GermanyDepartment of Electrical and Computer Engineering, University of Massachusetts Amherst, Amherst, MA, USAInstitute for Numerical Simulation, University of Bonn, Bonn, GermanyMachine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.https://ieeexplore.ieee.org/document/9007737/Explainable machine learninginformed machine learninginterpretabilityscientific consistencytransparency |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ribana Roscher Bastian Bohn Marco F. Duarte Jochen Garcke |
spellingShingle |
Ribana Roscher Bastian Bohn Marco F. Duarte Jochen Garcke Explainable Machine Learning for Scientific Insights and Discoveries IEEE Access Explainable machine learning informed machine learning interpretability scientific consistency transparency |
author_facet |
Ribana Roscher Bastian Bohn Marco F. Duarte Jochen Garcke |
author_sort |
Ribana Roscher |
title |
Explainable Machine Learning for Scientific Insights and Discoveries |
title_short |
Explainable Machine Learning for Scientific Insights and Discoveries |
title_full |
Explainable Machine Learning for Scientific Insights and Discoveries |
title_fullStr |
Explainable Machine Learning for Scientific Insights and Discoveries |
title_full_unstemmed |
Explainable Machine Learning for Scientific Insights and Discoveries |
title_sort |
explainable machine learning for scientific insights and discoveries |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas. |
topic |
Explainable machine learning informed machine learning interpretability scientific consistency transparency |
url |
https://ieeexplore.ieee.org/document/9007737/ |
work_keys_str_mv |
AT ribanaroscher explainablemachinelearningforscientificinsightsanddiscoveries AT bastianbohn explainablemachinelearningforscientificinsightsanddiscoveries AT marcofduarte explainablemachinelearningforscientificinsightsanddiscoveries AT jochengarcke explainablemachinelearningforscientificinsightsanddiscoveries |
_version_ |
1724185701281431552 |