Scholarlink

<p>Soil bulk density (ρ<sub>b</sub>) is vital for assessing soil organic carbon (SOC) and nutrient stocks, as well as for modeling soil processes. Although ρ<sub>b</sub> can be measured using traditional methods, these are labor-intensive and time-consuming. Consequently, there is a growing interest in developing pedotransfer functions (PTFs) to predict ρ<sub>b</sub> based on more easily measured soil properties. The vast Brazilian territory, with different climates and biomes, presents a challenge for development of national-scale PTFs, particularly for ρ<sub>b</sub>. In this study, a comprehensive dataset was compiled from various sources to develop ρ<sub>b</sub> PTFs across Brazil. The dataset includes particle size distribution (PSD), SOC, ρ<sub>b</sub>, sampling depth, soil order, land use, and geographic coordinates, allowing for the incorporation of additional numerical and categorical variables. Rigorous data preprocessing ensured quality and reliability. PTFs were developed using multiple linear regression (MLR) and Random Forest (RF) models. Model accuracy was evaluated using mean absolute error, bias, root mean square error (RMSE), and coefficient of determination. Both MLR and RF models accurately predicted ρ<sub>b</sub>, with log-transformed PSD and SOC emerging as key predictors. The RF model slightly outperformed the MLR model (RMSE = 0.12 vs. 0.13&#xa0;g&#xa0;cm<sup>−3</sup>) on the test dataset, underscoring the importance of environmental and categorical variables in predicting ρ<sub>b</sub>. The developed PTFs, along with other PTFs for Brazil, were applied to estimate SOC stocks across different biomes and land uses. Best estimations were obtained with the RF model, with an R<sup>2</sup> of 0.97, emphasizing the value of categorical variables in improving SOC stock estimations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting bulk density in Brazilian soils for carbon stocks calculation: a comparative study of multiple linear regression and Random Forest models using continuous and categorical variables

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月3日

查看全文
  • Wharley Pereira dos Santos,
  • Carlos Manoel Pedro Vaz,
  • Ladislau Martin-Neto,
  • Adriano Anselmi,
  • Javier Tomasella,
  • Falberni de Souza Costa,
  • Jackson Adriano Albuquerque,
  • Quirijn de Jong van Lier,
  • Rafael Galbieri,
  • Fabiano José Perina

摘要

Soil bulk density (ρb) is vital for assessing soil organic carbon (SOC) and nutrient stocks, as well as for modeling soil processes. Although ρb can be measured using traditional methods, these are labor-intensive and time-consuming. Consequently, there is a growing interest in developing pedotransfer functions (PTFs) to predict ρb based on more easily measured soil properties. The vast Brazilian territory, with different climates and biomes, presents a challenge for development of national-scale PTFs, particularly for ρb. In this study, a comprehensive dataset was compiled from various sources to develop ρb PTFs across Brazil. The dataset includes particle size distribution (PSD), SOC, ρb, sampling depth, soil order, land use, and geographic coordinates, allowing for the incorporation of additional numerical and categorical variables. Rigorous data preprocessing ensured quality and reliability. PTFs were developed using multiple linear regression (MLR) and Random Forest (RF) models. Model accuracy was evaluated using mean absolute error, bias, root mean square error (RMSE), and coefficient of determination. Both MLR and RF models accurately predicted ρb, with log-transformed PSD and SOC emerging as key predictors. The RF model slightly outperformed the MLR model (RMSE = 0.12 vs. 0.13 g cm−3) on the test dataset, underscoring the importance of environmental and categorical variables in predicting ρb. The developed PTFs, along with other PTFs for Brazil, were applied to estimate SOC stocks across different biomes and land uses. Best estimations were obtained with the RF model, with an R2 of 0.97, emphasizing the value of categorical variables in improving SOC stock estimations.