Prediction of soil stresses and compaction due to agricultural machines in sugarcane cultivation systems with and without crop rotation.

One strategy to eliminate or minimize occurrence of soil compaction in sugarcane production is through modelling, which can identify the risk associated with different operations and machine equipment. Soil damage resulting from the passage of machines can be than reduced through preventive measures which focus on the soil-machine relationship. In the present study, the magnitudes and distribution of the stresses produced in the soil through the loads carried by the axles of the machines used in sugarcane cultivation systems were analysed and modelled. The Tyres/Track and Soil Compaction (TASC) tool took the soil and machine data, estimated contact areas and mean contact pressures at the soil-tyre/track interface, and associated with preconsolidation stress data obtained in the uniaxial test modelled the propagation of the applied stress into the soil. The traffic right after conventional tillage promotes soil compaction, while on areas with less intensive soil tillage, as the soil has greater load bearing capacity, the stress dissipates in the surface layers. There was a severe risk of soil compaction for three operations before sugarcane harvesting: crop rotations planting, harvesting of the peanut rotational crop, and planting of the sugarcane billets, with subsoil compaction extending down to 0.33 m. On harvesting, trailer has the higher potential to cause soil compaction, with a compressive stress of 157 kPa, at 0.21 m depth, greater than the preconsolidation pressure of all cultivation systems tested. Crop rotation systems associated with soil tillage that promote intense soil disaggregation increase the risk of soil compaction, which is not compensated by other advantages of such systems, and the soil is easily compacted by the subsequent agricultural machine traffic. The results indicate strategies to avoid soil compaction by machines used in sugarcane cultivation systems, including adjustments on machine loads and changes in tillage and management design.

Use of data mining techniques to classify soil CO2 emission induced by crop management in sugarcane field.

Soil CO2 emissions are regarded as one of the largest flows of the global carbon cycle and small changes in their magnitude can have a large effect on the CO2 concentration in the atmosphere. Thus, a better understanding of this attribute would enable the identification of promoters and the development of strategies to mitigate the risks of climate change. Therefore, our study aimed at using data mining techniques to predict the soil CO2 emission induced by crop management in sugarcane areas in Brazil. To do so, we used different variable selection methods (correlation, chi-square, wrapper) and classification (Decision tree, Bayesian models, neural networks, support vector machine, bagging with logistic regression), and finally we tested the efficiency of different approaches through the Receiver Operating Characteristic (ROC) curve. The original dataset consisted of 19 variables (18 independent variables and one dependent (or response) variable). The association between cover crop and minimum tillage are effective strategies to promote the mitigation of soil CO2 emissions, in which the average CO2 emissions are 63 kg ha-1 day-1. The variables soil moisture, soil temperature (Ts), rainfall, pH, and organic carbon were most frequently selected for soil CO2 emission classification using different methods for attribute selection. According to the results of the ROC curve, the best approaches for soil CO2 emission classification were the following: (I)-the Multilayer Perceptron classifier with attribute selection through the wrapper method, that presented rate of false positive of 13,50%, true positive of 94,20% area under the curve (AUC) of 89,90% (II)-the Bagging classifier with logistic regression with attribute selection through the Chi-square method, that presented rate of false positive of 13,50%, true positive of 94,20% AUC of 89,90%. However, the (I) approach stands out in relation to (II) for its higher positive class accuracy (high CO2 emission) and lower computational cost.