Received: 02 Apr 2020 – Discussion started: 07 May 2020
Abstract. The understanding of water quality and its underlying processes is important for the protection of aquatic environments. Here an explainable AI (XAI) based multivariate time series analytical framework is applied on high-frequency water quality measurements including nitrate and electrical conductivity and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by a cluster analysis which does not depend on prior knowledge about data structure. The cluster analysis is designed to find similar days within a cluster and dissimilar days between clusters. This allows for the data-driven choice of a distance measure. Using a swarm based AI system, the resulting cluster define three states of water bodies, which can be visualized by a topographic map of high-dimensional structures. These structures are explained by rules extracted from decision trees. The rules generated by the XAI system improve the understanding of aquatic environments. The model description presented here allows to extract meaningful, useful, and new knowledge from multivariate time series.
Datasets of ExplainableAI4KnowledgeAcquisitionStreamTS2020: Analytic Procedure for Explainable AI for Knowledge Acquisition in Hydrochemical Time SeriesM. Thrun and A. Ultsch https://doi.org/10.5281/zenodo.3734892
ExplainableAI4KnowledgeAcquisitionStreamTS2020: Analytic Procedure for Explainable AI for Knowledge Acquisition in Hydrochemical Time SeriesM. Thrun and A. Ultsch https://doi.org/10.5281/zenodo.3734892
Michael C. Thrun et al.
Viewed
Total article views: 763 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
444
270
49
763
51
51
HTML: 444
PDF: 270
XML: 49
Total: 763
BibTeX: 51
EndNote: 51
Views and downloads (calculated since 07 May 2020)
Cumulative views and downloads
(calculated since 07 May 2020)
Viewed (geographical distribution)
Total article views: 662 (including HTML, PDF, and XML)
Thereof 660 with geography defined
and 2 with unknown origin.
We propose an explainable AI (XAI) framework for times series describing water quality & environmental parameters. The relationship between parameters is investigated by swarm based cluster analysis designed to find similar days within & dissimilar days between clusters. Resulting clusters define three states of water bodies & are visualized by a topographic map of high-dimensional structures. Rules generated by the XAI system explain clusters & improve the understanding of aquatic environments.
We propose an explainable AI (XAI) framework for times series describing water quality &...