A tree regression analysis of factors determining the sorption and retention of heavy metals by soil

Covelo, Emma F.; Matías, J. M.; Vega, F.A.; Reigosa, Manuel J.; Andrade, Liliana María

doi:10.1016/j.geoderma.2008.08.001

Cited by 36 publications

(34 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gruszczynski (2005) examined the soil spatial distribution pollution of Chromium (Cr) where pollution by this element was high using interpolation algorithms and artificial neural networks. Covelo et al (2008) examined the tree fitted regression models on the data containing six heavy metal. The sorption and retention of mixtures of heavy metals was reproduced by binary decisiontree regression models using classification and regression trees (CART) algorithm by an accompanying paper of Vega et al (2009).…”

Section: Introductionmentioning

confidence: 99%

Using multivariate adaptive regression splines to estimate pollution in soil

Kılınç

Malkoç²,

Koparal

et al. 2017

Int. j. adv. appl. sci

View full text Add to dashboard Cite

Heavy metal pollution is one of the main factors of the traffic pollution. The public authorities have been monitoring the concentration of heavy metal by means of sampling stations. This paper describes the response surface models and an intelligent regression algorithm, multivariate adaptive regression splines (MARS) models to data collected from soil at the stations where there were high density of buildings, roads, traffic and tramways. The model variables included the number of car and tramways and the concentration levels of Cadmium (Cd), Zinc (Zn) and Lead (Pb), at depth of 0-100mm. The objective of this study was to apply MARS to analyze the model output when there are a few numbers of design points. Several MARS models developed to simulate the concentration of each heavy metal. The performance of MARS was compared to that of response surface methodology (RSM) using 1 st and 2 nd order response surface models with respect to the accuracy metrics; root mean square error and adjusted R 2 . The results showed that MARS models were successful in goodness of fit, suitable and also reliable as compared to the RSM models. Additionally, use of MARS in selection of the variables indicating great contribution on the response was effective.

show abstract

Section: Introductionmentioning

confidence: 99%

Using multivariate adaptive regression splines to estimate pollution in soil

Kılınç

Malkoç²,

Koparal

et al. 2017

Int. j. adv. appl. sci

View full text Add to dashboard Cite

show abstract

“…The results of the model experiment indicate the highest Pb sorption in single-metal experiment as well as in multi-metal one in Chernozem. In general, the sorption of Pb and Cu was higher than Cd and Zn sorption (Covelo et al 2008). The sorption concentration of Zn was 10-times lower in the presence of other competitive metals.…”

Section: Resultsmentioning

confidence: 86%

A model experiment: competitive sorption of Cd, Cu, Pb and Zn by three different soils

Zemanová¹,

Trakal

Ochecova³

et al. 2014

Soil Water Res.

View full text Add to dashboard Cite

Zemanová V., Trakal L., Ochecová P., Száková J., Pavlíková D. (2014) The results of the model experiment confirmed that the sorption from single-metal solution was more effective than sorption under multi-metal conditions, due to competitive effects. In all tested soils sorption of Cd, Cu and Zn decreased with the rate of other competitive metals; the Pb sorption was not affected by other competitive metals in solutions. Moreover, during multi-metal sorption, Zn was significantly desorbed in Cambisol. In general, sorptions of Cu, Pb and Zn were greater in uncontaminated soil compared to contaminated soils. Clear trend of impact of the contamination on Cd sorption was not observed. The results showed the sorption decreasing in order Chernozem > Fluvisol > Cambisol. The sorption was the greatest in uncontaminated soil with low mobility of studied metals.

show abstract

“…Para el análisis estadístico se utilizó la técnica de árboles de clasificación y, entre ellos, los estructurados binarios (Breiman et al, 1984;Covelo et al, 2008;Vega et al, 2009), que son construidos por divisiones repetidas de subconjuntos de X en dos subconjuntos descendientes, comenzando con X mismo (Fig. 1).…”

Section: Materiales Y Métodosunclassified

“…Se considera como el número de casos en la clase j. Sean las probabilidades a priori tomadas como las proporciones En un nodo t, comprendido como punto de conexión entre dos o más elementos del árbol, sea el número total de casos en L con t x n ∈ y el número de casos de la clase j en t. La proporción de los casos de la clase j en L que caen dentro de t es Para un conjunto a priori dado, es interpretado como la probabilidad de que un caso en la clase j estará presente en el árbol. Se toma como el estimador por resustitución para la probabilidad de que un caso estará en la clase j y caiga dentro del nodo t. El estimador por re-sustitución p (t) de la probabilidad de que cualquier caso caiga dentro del nodo t es definido (Breiman et al, 1984;Covelo et al, 2008) por:…”

Section: Construcción Del áRbolunclassified

“…Por lo tanto, el objetivo de este estudio es explorar si el estadio sexual de los organismos se puede identificar con herramientas estadísticas que puedan describir la composición y comportamiento de las poblaciones. En este estudio se utiliza una nueva técnica, que pertenece a la rama del análisis multivariado, que es la de árboles de clasificación (Breiman et al, 1984;Covelo et al, 2008;Vega et al, 2009). La técnica comienza suponiendo probabilidades a priori de igual tamaño para, en el presente caso, las tres clases de individuos (indiferenciados, machos y hembras) y se calcula una probabilidad de resustitución para determinar, con cada variable, la división binaria que puede establecerse primero en el nodo raíz y subsecuentemente en los modos posteriores.…”

unclassified

See 1 more Smart Citation

Arboles de clasificacion de Potimirim mexicana (Decapoda: Caridea), organismo hermafrodita protandrico secuencial

Bortolini¹,

Alonso²,

Álvarez³

2013

lajar

View full text Add to dashboard Cite

RESUMEN.Se presenta un análisis estadístico de variables morfométricas del camarón de agua dulce Potimirim mexicana, que ha sido descrito como hermafrodita protándrico secuencial. El objetivo es probar estadísticamente, que los organismos pueden ser clasificados por sexo, analizando su longitud y otras variables morfológicas. Un total de 191 organismos fueron capturados en el río Máquinas, Veracruz, México. La técnica utilizada fue la de árboles de clasificación, que mediante probabilidades van determinando las variables significativas en la variable "respuesta", así como las que son necesarias para la discriminación. Esta técnica permitió corroborar la teoría que la longitud total del organismo es necesaria para la discriminación de la variable sexo, pero también generó el resultado que, estadísticamente, dos variables más son importantes en este proceso discriminatorio; el largo del segundo pleópodo y largo del carpo del tercer pereiópodo. La técnica generó un clasificación correcta de 82% utilizando las tres variables mencionadas. Lo significativo del proceso es que al generar los árboles de clasificación se muestran, de manera sencilla y práctica, las variables necesarias en este proceso, así como su nivel discriminatorio individual. Palabras clave: árboles de clasificación, Potimirim mexicana, Atyidae, Caridea.Classification trees of Potimirim mexicana (Decapoda: Caridea), a sequential protandrous hermaphrodite organism ABSTRACT. A statistical analysis of several morphometric variables of the freshwater shrimp Potimiirim mexicana, which has been described as a sequential protandrous hermaphrodite, is presented. The purpose of the study is to test, statistically, that organisms can be classified by sex, analyzing their size and other morphological variables. A total of 191 organisms were collected in the Máquinas River, Veracruz, Mexico. The technique used was that of classification trees, through which will likely determines the significant variables in the variable "response", as well as those required for discrimination. This technique corroborated the theory that the total length of the body is necessary for discrimination of the sex variable, but also brought the result that, statistically, two more variables are important in this discriminatory process, the length of the second pleopod and length of the carpus of the third pereiopod. The technique resulted in a correct classification of 82% using the three variables. What is significant is that the process generating the classification tree shown, in a simple and practical manneer, the variables necessary for this process and their individual discriminatory power. Keywords: classification trees, Potimirim mexicana, Atyidae, Caridea. ___________________Corresponding author: Fernando Alvarez (falvarez@unam.mx) INTRODUCCIÓNLos crustáceos presentan especies dioicas o de sexos separados, pero también existen especies hermafroditas simultáneas o secuenciales (Maynard, 1979;De Almeida & Buckup, 2000). Los hermafroditas secuenciales pueden, a su vez, ser protá...

show abstract

A tree regression analysis of factors determining the sorption and retention of heavy metals by soil

Cited by 36 publications

References 25 publications

Using multivariate adaptive regression splines to estimate pollution in soil

Using multivariate adaptive regression splines to estimate pollution in soil

A model experiment: competitive sorption of Cd, Cu, Pb and Zn by three different soils

Arboles de clasificacion de Potimirim mexicana (Decapoda: Caridea), organismo hermafrodita protandrico secuencial

Contact Info

Product

Resources

About