Predicting total phosphorus levels as indicators for shallow lake management

The discusser thanks the authors for investigating the ability of modified random forest algorithm to predicting total phosphorus levels as indicators for shallow lake management. The abilities of machine learning techniques such as optimization algorithms today have been well documented in engineer...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Ecological indicators Jg. 107; S. 105664
1. Verfasser:	Mohammadi, Babak
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.12.2019
Schlagworte:	Algorithm’s parameters Data mining technique Random forest Variable selection Data mining technique Random forest Algorithm’s parameters Variable selection
ISSN:	1470-160X, 1872-7034
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The discusser thanks the authors for investigating the ability of modified random forest algorithm to predicting total phosphorus levels as indicators for shallow lake management. The abilities of machine learning techniques such as optimization algorithms today have been well documented in engineering sciences. In this discussion, the discusser has tried to clarify the process of the paper of “Predicting total phosphorus levels as indicators for shallow lake management”(doi: https://doi.org/10.1016/j.ecolind.2018.09.002). The discusser would like to call attention to some important points, which may be taken into consideration by the authors and other potential researchers.
ISSN:	1470-160X 1872-7034
DOI:	10.1016/j.ecolind.2019.105664