Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/335911 
Autor:innen: 
Erscheinungsjahr: 
2025
Verlag: 
The Unjournal, s.l.
Zusammenfassung: 
This paper aims to model and predict the global potential for natural regeneration in deforested tropical regions for 2016 and 2030, respectively, using a machine learning random forest (RF) approach. The study’s aim and methods are novel and important, given the potential benefits of natural regeneration on carbon sequestration (amongst many other ecological and environmental outcomes) and the lack of pan-tropical analysis. The paper's current estimates are the first we have for understanding the scope of natural regeneration as an effective climate change mitigation measure.However, my review identifies several significant conceptual and methodological concerns that fundamentally affect the validity and interpretability of the results and predictions, particularly concerning the paper's goal of informing restoration prioritization.
Persistent Identifier der Erstveröffentlichung: 
Creative-Commons-Lizenz: 
cc-by Logo
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe





Publikationen in EconStor sind urheberrechtlich geschützt.