Regressão linear múltipla e modelo Random Forest para estimar a densidade do solo em áreas montanhosas

Abstract

Resumo -O objetivo deste trabalho foi o desenvolvimento de modelos com diferentes conjuntos de dados, para estimar a densidade de solos de regiões tropicais montanhosas, a partir de atributos de solos comumente encontrados nas análises de perfis de solos descritos nos levantamentos regionais. O conjunto total de dados compõe-se de 163 amostras e foi dividido em seis grupamentos, dos quais três com 73 amostras, com o máximo de 32 covariáveis, e três com 163 amostras, com o máximo de 18 covariáveis. Testaram-se modelos de regressão linear múltipla (RLM) e randomForest (RF). A menor incerteza entre os modelos foi alcançada pelo RLM2, com R 2 de 0,56, 13 covariáveis e 73 amostras. Nos grupamentos com 163 amostras, os melhores modelos foram os RF, com R 2 médio de 0,48. A raiz quadrada da média do erro ao quadrado variou entre 0,09 e 0,14. As covariáveis mais importantes no modelo RF foram: carbono orgânico, hidrogênio, areia fina e grossa, saturação por bases e capacidade de troca catiônica. Pelo método "stepwise regression", as variáveis mais importantes foram: a relação silte/argila; areia grossa e fina; carbono orgânico; saturação por bases; e potássio.Termos para indexação: estoque de carbono, funções de pedotransferência, modelos dirigidos pelos dados, stepwise. Multiple linear regression and Random Forest model to estimate soil bulk density in mountainous regionsAbstract -The objective of this work was the development of models with different sets of data for estimating soil bulk density in tropical mountainous regions, from soil attributes commonly found in the analyses of soil profiles described in regional surveys. The complete dataset is composed of 163 samples and it was divided into six groups, of which three groups have 73 samples and the maximum of 32 covariables, and three have 163 samples and the maximum of 18 covariables. The linear regression (RLM) and randomForest (RF) models were tested. The lowest uncertainty between the models was achieved by RLM2, with R 2 of 0.56, 13 covariables, and 73 samples. Considering the groups with 163 samples, the best models were the RFs with mean R 2 of 0.48. The root mean squared error ranged between 0.09 and 0.14. The most important covariables in the RF model were: organic carbon, hydrogen, fine and coarse sand, base saturation, and cation exchange capacity. By the stepwise backward regression, the main covariables were: silt and clay relation; fine and coarse sand; organic carbon; base saturation; and potassium.

Mapping soil properties in a poorly-accessible area

“…This can be related to the limited access to regions located to the North and West of INP, consequently a small number of soil samples, with some covariates having high variations (DEM). Similar results were observed by Chagas et al (2016) andCarvalho Junior et al (2016), when comparing Random Forest and MLR, regression seems to extrapolate the values. Like MLR, GAM models tend to extrapolate the extreme values.…”

“…MLR: four models were fitted: one with all covariates (MLR_full); with covariates selection by correlation less than 0.85 between covariates (MLR_cor); other with the popular technique used in regression models, AIC (Akaike's Information Criterion) stepwise selection (Carvalho Junior et al, 2016;Chagas et al, 2016;Vermeulen and Niekerk, 2017) (MLR_step); and the technique of Recursive Feature Elimination (RFE) (MLR_RFE).…”

“…This suggests that selection algorithm using the function (rfe) for linear models in the caret package should be used carefully. In general, the best way to select covariates for MLR is the stepwise selection with AIC criteria, a common method to select models in linear regression (Carvalho Junior et al, 2016;Chagas et al, 2016;Vermeulen and Niekerk, 2017).…”

Development of a Computational Model to Predict Excess Body Fat in Adolescents through Low Cost Variables

“…Thus, we built a method to assess nutritional status in adolescents by estimating body fat percentage using low cost and easy application parameters. The method used for estimation was the MLR, which was already successfully applied to solve several problems such as clinical data analysis [47] to verify the association between autonomic cardiac function and clinical variables [49]; to investigate the effects of food contamination on gastrointestinal tract morbidity [50]; and soil density measurement [48].…”

“…In many areas of knowledge, such as engineering and health, many problems involve investigating the relationship between two or more variables [47,48,49,50]. Multiple linear regression (MLR) is a statistical technique widely used in the literature to verify the relationship between a dependent variable and several independent variables [51].…”