<abstract xmlns="http://www.w3.org/1999/xhtml">The paper presents an application of interpretative machine learning to identify groups of lakes not with similar features but with similar potential factors influencing the content of total phosphorus – <italic>P</italic>tot. The method was developed on a sample of 60 lakes from North-Eastern Poland and used 25 external explanatory variables. Selected variables are stable over a long time, first group includes morphometric parameters of lakes and the second group encompass watershed geometry geology and land use. Our method involves building a regression model, creating an explainer, finding a set of mapping functions describing how each variable influences the outcome, and finally clustering objects by ’the influence’. The influence is a non-linear and non-parametric transformation of the explanatory variables into a form describing a given variable impact on the modeled feature. Such a transformation makes group data on the functional relations between the explanatory variables and the explained variable possible. The study reveals that there are five clusters where the concentration of <italic>P</italic>tot is shaped similarly. We compared our method with other numerical analyses and showed that it provides new information on the catchment area and lake trophy relationship.</abstract>

The paper presents an application of interpretative machine learning to identify groups of lakes not with similar features but with similar potential factors influencing the content of total phosphorus – Ptot. The method was developed on a sample of 60 lakes from North-Eastern Poland and used 25 external explanatory variables. Selected variables are stable over a long time, first group includes morphometric parameters of lakes and the second group encompass watershed geometry geology and land use. Our method involves building a regression model, creating an explainer, finding a set of mapping functions describing how each variable influences the outcome, and finally clustering objects by ’the influence’. The influence is a non-linear and non-parametric transformation of the explanatory variables into a form describing a given variable impact on the modeled feature. Such a transformation makes group data on the functional relations between the explanatory variables and the explained variable possible. The study reveals that there are five clusters where the concentration of Ptot is shaped similarly. We compared our method with other numerical analyses and showed that it provides new information on the catchment area and lake trophy relationship.

Interpretative Machine Learning as a Key in Recognizing the Variability of Lakes Trophy Patterns

Institute of Geoecology and Geoinformatics

Institute of Geography and Spatial Organization

Quaestiones Geographicae

This work is licensed under the Creative Commons Attribution 4.0 International License.

The paper presents an application of interpretative machine learning to identify groups of lakes not with similar features but with similar potential factors...

Interpretative Machine Learning as a Key in Recognizing the Variability of Lakes Trophy Patterns

Online veröffentlicht: 01. Apr. 2022

Seitenbereich: 127 - 146

Eingereicht: 14. Feb. 2022

DOI: https://doi.org/10.2478/quageo-2022-0009

Schlüsselwörter
total phosphorus, interpretative machine learning, random forest, Masurian lakes

© 2022 Jarosław Jasiewicz et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Interpretative Machine Learning as a Key in Recognizing the Variability of Lakes Trophy Patterns

Online veröffentlicht: 01. Apr. 2022

Seitenbereich: 127 - 146

Eingereicht: 14. Feb. 2022

DOI: https://doi.org/10.2478/quageo-2022-0009

Schlüsselwörtertotal phosphorus, interpretative machine learning, random forest, Masurian lakes

© 2022 Jarosław Jasiewicz et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
total phosphorus, interpretative machine learning, random forest, Masurian lakes