Explainable Machine Learning for Scientific Insights and Discoveries

By Ribana Roscher, Bastian Bohn, Marco F. Duarte, Jochen Garcke. 2019

856 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems and Management, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

In Materials Chemistry

Citations in the corpus

Recent advances in decision trees: an updated survey (2022, background): “With the growing ubiquity of machine learning and automated decision systems, there has been a rising interest in explainable machine learning : building models that can be, in some sense, understood by humans (Rudin 2019; Roscher et al. 2020).”
PhyGeoNet: Physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain (2020, background): “Physics-informed fully-connected neural networks Generally, training of a DNN model requires a vast amount of labeled data, which are often unavailable in many scientific machine learning (SciML) applications [9–12].”
Addressing bias in big data and AI for health care: A call for open science (2021, background): “66 Explainable AI by contrast includes interpretable AI models, where the strengths and weaknesses of a decision-making process are transparent.”
Deep-learning seismology (2022, background): “…goals of the community ( 139 ), but presenting the properties of these models in understandable terms to humans (interpretability) and revealing the underlying reasons for their output decision (explainability) ( 140 ) would allay such skep-ticism and lead to wider adoption and new insights.”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “With machine learning models becoming more and more complex, there is also a growing need for models to be interpretable and explainable [9].”
Improved Code Summarization via a Graph Neural Network (2020, background): “explainability is a prerequisite to ensure the scientic value of the outcome”[46].”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “Some argue that the terms are closely related but distinguish between them [21, 85, 181, 225], although there is no consensus on what the distinction exactly is [25].”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “Only recently, the technologies have become available to extract scientific insights from complex nonlinear models [121], [150], [166].”
Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation (2019, neutral): “…focus on this research area and refer the reader to survey papers on interpretable and explainable machine learning to other bodies of work (Rudin et al. 2022, Došilović et al. 2018, Guidotti et al. 2018b, Arya et al. 2020, Tjoa and Guan 2020, Roscher et al. 2020, Burkart and Huber 2021).”
The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, neutral): “These two terms, usually used interchangeably in the literature, refer to the ability of a model developer to make sense of why the model functions the way it does and to explain that to a user (Rudin, 2019; Samek and Müller, 2019; Roscher et al., 2020).”
On scientific understanding with artificial intelligence (2022, background): “[85] Ribana Roscher, Bastian Bohn, Marco F Duarte,”