Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land

The alternations in soil physicochemical properties caused by the reclamation of coastal tidal land can strongly affect the activities of soil extracellular enzymes. Soil extracellular enzymes are one of the most active organic components in soil ecosystem, which is involved in almost all the bioche...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuefeng Xie, Tao Wu, Ming Zhu, Guojun Jiang, Yan Xu, Xiaohan Wang, Lijie Pu
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Soil extracellular enzyme Coastal reclamation Random forest model Multiple linear regression Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/07dff582597943aa80a1d50cb9ec3e53
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:07dff582597943aa80a1d50cb9ec3e53
record_format	dspace
spelling	oai:doaj.org-article:07dff582597943aa80a1d50cb9ec3e532021-12-01T04:29:27ZComparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land1470-160X10.1016/j.ecolind.2020.106925https://doaj.org/article/07dff582597943aa80a1d50cb9ec3e532021-01-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X20308645https://doaj.org/toc/1470-160XThe alternations in soil physicochemical properties caused by the reclamation of coastal tidal land can strongly affect the activities of soil extracellular enzymes. Soil extracellular enzymes are one of the most active organic components in soil ecosystem, which is involved in almost all the biochemical reactions. Determining the importance of potential influencing factors of soil extracellular enzymes and thus estimating their activities are important for clarifying the biological mechanism of soil carbon and nitrogen cycling. In this study, the multiple linear regressions (MLR) and random forest (RF) models were conducted to estimate the activities of soil amylase and urease activities using covariates, such as soil water content (SWC), electrical conductivity (EC), total nitrogen (TN), total phosphorus (TP), and soil organic carbon (SOC) as well as the soil bulk density (BD) and pH. The results reveals that the amylase activity of fishpond was significantly higher than that of other land use types, while the urease activity of rape land, broad bean land, and fishpond were notably higher than that of bare flat, Spartina alterniflora, and uncultivated land. The RF model indicated that the SWC and TN is the main variable affecting amylase and urease activity, respectively. The RF model performed much better than MLR model in estimating the soil amylase and urease activity as it revealed much lower error indices (MAE and RMSE) and higher R2 value. The superiority of RF model in estimating amylase and urease activity is due to its advantages to handle the nonlinear and hierarchical relationships between enzyme activities and covariates, and insensitivity to overfitting and the presence of noise in the data.Xuefeng XieTao WuMing ZhuGuojun JiangYan XuXiaohan WangLijie PuElsevierarticleSoil extracellular enzymeCoastal reclamationRandom forest modelMultiple linear regressionEcologyQH540-549.5ENEcological Indicators, Vol 120, Iss , Pp 106925- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Soil extracellular enzyme Coastal reclamation Random forest model Multiple linear regression Ecology QH540-549.5
spellingShingle	Soil extracellular enzyme Coastal reclamation Random forest model Multiple linear regression Ecology QH540-549.5 Xuefeng Xie Tao Wu Ming Zhu Guojun Jiang Yan Xu Xiaohan Wang Lijie Pu Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
description	The alternations in soil physicochemical properties caused by the reclamation of coastal tidal land can strongly affect the activities of soil extracellular enzymes. Soil extracellular enzymes are one of the most active organic components in soil ecosystem, which is involved in almost all the biochemical reactions. Determining the importance of potential influencing factors of soil extracellular enzymes and thus estimating their activities are important for clarifying the biological mechanism of soil carbon and nitrogen cycling. In this study, the multiple linear regressions (MLR) and random forest (RF) models were conducted to estimate the activities of soil amylase and urease activities using covariates, such as soil water content (SWC), electrical conductivity (EC), total nitrogen (TN), total phosphorus (TP), and soil organic carbon (SOC) as well as the soil bulk density (BD) and pH. The results reveals that the amylase activity of fishpond was significantly higher than that of other land use types, while the urease activity of rape land, broad bean land, and fishpond were notably higher than that of bare flat, Spartina alterniflora, and uncultivated land. The RF model indicated that the SWC and TN is the main variable affecting amylase and urease activity, respectively. The RF model performed much better than MLR model in estimating the soil amylase and urease activity as it revealed much lower error indices (MAE and RMSE) and higher R2 value. The superiority of RF model in estimating amylase and urease activity is due to its advantages to handle the nonlinear and hierarchical relationships between enzyme activities and covariates, and insensitivity to overfitting and the presence of noise in the data.
format	article
author	Xuefeng Xie Tao Wu Ming Zhu Guojun Jiang Yan Xu Xiaohan Wang Lijie Pu
author_facet	Xuefeng Xie Tao Wu Ming Zhu Guojun Jiang Yan Xu Xiaohan Wang Lijie Pu
author_sort	Xuefeng Xie
title	Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
title_short	Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
title_full	Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
title_fullStr	Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
title_full_unstemmed	Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
title_sort	comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/07dff582597943aa80a1d50cb9ec3e53
work_keys_str_mv	AT xuefengxie comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT taowu comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT mingzhu comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT guojunjiang comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT yanxu comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT xiaohanwang comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland AT lijiepu comparisonofrandomforestandmultiplelinearregressionmodelsforestimationofsoilextracellularenzymeactivitiesinagriculturalreclaimedcoastalsalineland
_version_	1718405883606597632

Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land

Ejemplares similares