Table 1.
Description of the 19 variables (independent and dependent) used in the database composition.
Table 2.
Distribution of CO2 emission (kg ha-1 dia-1) according to the low, medium and high classes and their limits.
Fig 1.
Discretization of CO2 emission from the soil in the positive class (CO2 emissions from high soil) and the negative classes (medium and low CO2 emissions).
Fig 2.
Demonstration of the classes distribution before and after the application of the NCL filter.
Table 3.
TP = true positive; FP = false positive; FN = false negative; TN = true negative.
Fig 3.
(A) Temporal variability of soil CO2 emission and rainfall, and (B) average soil CO2 emission with their respective standard deviations, in the different management systems used in the experimental area. CTCC = Conventional tillage with cover crop, MTCC = Minimal tillage with cover crop, CTWC = Conventional tillage without cover crop, MTWC = Minimal tillage without cover crop.
Fig 4.
Box plot for the physical variables of the soil in the different management systems used in the experimental area.
CTCC = Conventional tillage with cover crop, MTCC = Minimal tillage with cover crop, CTWC = Conventional tillage without cover crop, MTWC = Minimal tillage without cover crop. Sm = Soil moisture, St = Soil temperature, MDA = Mean diameter of the aggregate, Macro = Soil macroporosity, Micro = Soil microporosity, TP = Total porosity, Bd = Bulk density, PR = Penetration resistance, Ts = Tensile strength of the aggregate.
Fig 5.
Box plot for soil chemical and biological variables in the different management systems used in the experimental area.
CTCC = Conventional tillage with cover crop, MTCC = Minimal tillage with cover crop, CTWC = Conventional tillage without cover crop, MTWC = Minimal tillage without cover crop, H+Al = Acidity potential, Al+3 = Exchangeable aluminum, Ca+2 = Exchangeable calcium, Mg+2 = Exchangeable magnesium, K+ = Exchangeable potassium, P = Exchangeable phosphorus, Organic C = Organic Carbon, MBC = Microbial biomass carbon.
Table 4.
Variables selected through the different selection methods.
Table 5.
The performance of different classifiers associated with the attribute selection methods assessed.
Table 6.
Rate of false positive (FP), true positive (TP) area under the curve (AUC) for the best associations between classification and attribute selection method.
Fig 6.
Performance in the ROC (Receiver Operating Characteristic) space of the different approaches used to classify soil CO2 emission, considering the high CO2 emission class as the "most important" class.
I = J48 with χ2, II = Naïve Bayes with χ2, III = Bagging with logistic regression with χ2, IV = SMO using wrapper method, V = Multilayer Perceptron with wrapper method.