Next Article in Journal
Property Checking with Interpretable Error Characterization for Recurrent Neural Networks
Previous Article in Journal
Acknowledgment to Reviewers of MAKE in 2020
Article

Explainable AI Framework for Multivariate Hydrochemical Time Series

1
Databionics Research Group, Department of Mathematics and Computer Science, University of Marburg, 35043 Marburg, Germany
2
Department of Hematology, Oncology and Immunology, University of Marburg, 35043 Marburg, Germany
3
Institute for Landscape Ecology and Resources Management (ILR), Research Centre for BioSystems, Land Use and Nutrition (iFZ), Justus Liebig University Giessen, Heinrich-Buff-Ring 26, 35392 Gießen, Germany
4
Centre for International Development and Environmental Research (ZEU), Justus Liebig University Giessen, Senckenbergstrasse 3, 35390 Giessen, Germany
*
Author to whom correspondence should be addressed.
Mach. Learn. Knowl. Extr. 2021, 3(1), 170-204; https://0-doi-org.brum.beds.ac.uk/10.3390/make3010009
Received: 30 December 2020 / Revised: 26 January 2021 / Accepted: 27 January 2021 / Published: 4 February 2021
The understanding of water quality and its underlying processes is important for the protection of aquatic environments. With the rare opportunity of access to a domain expert, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series. The XAI provides explanations that are interpretable by domain experts. In three steps, it combines a data-driven choice of a distance measure with supervised decision trees guided by projection-based clustering. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The framework, called DDS-XAI, does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two state of the art XAIs called eUD3.5 and iterative mistake minimization (IMM) were unable to provide meaningful and relevant explanations from the three multivariate time series data. The DDS-XAI framework can be swiftly applied to new data. Open-source code in R for all steps of the XAI framework is provided and the steps are structured application-oriented. View Full-Text
Keywords: explainable AI; cluster analysis; structures in data; machine learning system; high-dimensional data visualization; decision trees explainable AI; cluster analysis; structures in data; machine learning system; high-dimensional data visualization; decision trees
Show Figures

Figure 1

  • Externally hosted supplementary file 1
    Doi: 10.5281/zenodo.4498241
    Link: https://zenodo.org/record/4498241
    Description: XAI Framework for Time Series with an Example Based on Hydrochemical Data
MDPI and ACS Style

Thrun, M.C.; Ultsch, A.; Breuer, L. Explainable AI Framework for Multivariate Hydrochemical Time Series. Mach. Learn. Knowl. Extr. 2021, 3, 170-204. https://0-doi-org.brum.beds.ac.uk/10.3390/make3010009

AMA Style

Thrun MC, Ultsch A, Breuer L. Explainable AI Framework for Multivariate Hydrochemical Time Series. Machine Learning and Knowledge Extraction. 2021; 3(1):170-204. https://0-doi-org.brum.beds.ac.uk/10.3390/make3010009

Chicago/Turabian Style

Thrun, Michael C., Alfred Ultsch, and Lutz Breuer. 2021. "Explainable AI Framework for Multivariate Hydrochemical Time Series" Machine Learning and Knowledge Extraction 3, no. 1: 170-204. https://0-doi-org.brum.beds.ac.uk/10.3390/make3010009

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop