Ecological state evaluation of lake ecosystems revisited: Latent variables with kSVM algorithm approach for assessment automatization and data comprehension



Chrobak, Grzegorz, Kowalczyk, Tomasz, Fischer, Thomas B ORCID: 0000-0003-1436-1221, Szewranski, Szymon, Chrobak, Katarzyna and Kazak, Jan K
(2021) Ecological state evaluation of lake ecosystems revisited: Latent variables with kSVM algorithm approach for assessment automatization and data comprehension. ECOLOGICAL INDICATORS, 125. p. 107567.

Access the full-text of this item by clicking on the Open Access link.

Abstract

Automated and reproducible methodology for assessing the ecological condition of lakes is essential for effective monitoring and facilitating the decision-making process aimed at achieving the stated environmental goals. At the same time, multidimensional measurement datasets are often an obstacle to drawing insightful conclusions, thus becoming an incentive for overly simplified analyzes. In this article, a set of measurements and ecological status assessment results for a collection of 499 lakes in Poland was used. Expert assessment process was recreated using the supervised kernel Support Vector Machine algorithm on dataset with reduced dimensionality, thus a model that automates the ecological assessment process was obtained. The use of the explanatory skill of latent variables made it possible to present the assessed objects along with their position in individual classes. The visualization of the results in reduced dimensionality increased, without interfering with the size of the classes, the informative evaluation potential, which should be considered as an acompanying assessment parameter in the future. The primary target of this paper is the ecological expert coping with automatization of assessment process and obtaining latent information for sense-making visual comprehension during consultations regarding ecosystem-oriented ecological decision making.

Item Type: Article
Uncontrolled Keywords: Ecological assessment, Lake ecosystems, Machine learning, Latent variable analysis, Ecosystems, Decision support
Divisions: Faculty of Science and Engineering > School of Environmental Sciences
Depositing User: Symplectic Admin
Date Deposited: 02 Sep 2021 07:21
Last Modified: 18 Jan 2023 21:30
DOI: 10.1016/j.ecolind.2021.107567
Open Access URL: https://doi.org/10.1016/j.ecolind.2021.107567
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3135607