Work

R scripts for GBM modelling of EDTA-extractable soil copper

Year: 2025

Type: software

Abstract: This repository contains the R scripts used to process the dataset and perform Boosted Regression Tree (GBM) modelling of EDTA-extractable copper concentrations in soils.The workflow includes:* data preparation and variable transformation* model training using Gradient Boosting Machines* internal cross-validation and external validation* hyperparameter tuning* comparison of multiple modelling scenarios* calculation of predictor relative influenceThe scripts are provided to ensure transparency and reproducibility of the modelling approach used in the associated scientific publication.

Source: HAL

Authors: Savignan, Lionel, Colin, Félix, Geoffroy, Vincent, Jalabert, Stéphanie, Lee, Alexandre, Chéry, Philippe

Institutions: École Nationale Supérieure des Sciences Agronomiques de Bordeaux-Aquitaine, Environnements et Paléoenvironnements Océaniques et Continentaux

Language: English

Topic: Heavy metals in environment

Subfield: Pollution

Field: Environmental Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7223078624

Cites:

Cited by:

Related to: 10