Classification of soil respiration in areas of sugarcane renewal using decision tree

Ana Paula Guimarães Santos,Camila Viana Vieira Farhate,Stanley Robson de Medeiros Oliveira,João Luís Nunes Carvalho,Newton La Scala Júnior,Zigomar Menezes de Souza

doi:10.1590/1678-992x-2016-0473

Abstract

The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soil moisture > potential acidity.

Highlights

Soil respiration is defined as carbon dioxide (CO2) released from the soil surface into the atmosphere through the combined activity of the roots and decomposing organisms of soil organic matter (Stockmann et al, 2013)
Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration
Two major peaks occurred in soil respiration during this period, which coincide with precipitation events one day before

Summary

Introduction

Soil respiration is defined as carbon dioxide (CO2) released from the soil surface into the atmosphere through the combined activity of the roots and decomposing organisms of soil organic matter (Stockmann et al, 2013). It is a significant component in the global carbon balance (C), since it is the main contributor in the transmission of C from the pedosphere into the atmosphere (Vicca et al, 2014). A more detailed understanding of the components of the global C balance allows to identify sources and drains of C and develop strategies to mitigate the risks of climate change (Lal, 2004). Estimating sequestration or soil respiration into the atmosphere in production systems is difficult and complex due to the diversity of agricultural practices in large areas and significant variations of both soil and climate (Smith et al, 2010)

Objectives

Methods

Results

Conclusion