Forecasting the spatiotemporal variability of soil CO2 emissions in sugarcane areas in southeastern Brazil using artificial neural networks

Carbon dioxide (CO2) is considered one of the main greenhouse effect gases and contributes significantly to global climate change. In Brazil, the agricultural areas offer an opportunity to mitigate this effect, especially with the sugarcane crop, since, depending on the management system, sugarcane stores large amounts of carbon, thereby removing it from the atmosphere. The CO2 production in soil and its transport to the atmosphere are the results of biochemical processes such as the decomposition of organic matter and roots and the respiration of soil organisms, a phenomenon called soil CO2 emissions (FCO2). The objective of the study was to investigate the use of neural networks with backpropagation algorithm to predict the spatial patterns of soil CO2 emission during short periods in sugarcane areas. FCO2 values were collected in three commercial crop areas in the SAo Paulo state, southeastern Brazil, registered through the LI-8100 system during the years 2008 (Motuca), 2010 (Guariba city), and 2012 (Pradopolis), in the period after the mechanical harvesting (green cane). A neural network multilayer perceptron with a backpropagation algorithm was applied to estimate the FCO2 in 2012, using data from 2008 and 2010 as training for the neural network. The neural network initially presented a mean absolute percentage error (MAPE) of 18.3852 and a coefficient of determination (R-2) of 0.9188. Data obtained from the observed and estimated values of FCO2 present moderate spatial dependence, and it is observed from the maps of the spatial pattern of the CO2 flow that the results from the neural network show considerable similarity to the observed data. The model results identify the higher and lower characteristics in sample points of CO2 emissions and produce an overestimation of the range of spatial dependence (0.45 m) and an underestimation of the interpolated values in the field (R-2 = 0.80; MAPE = 12.0591), when compared to the actual soil CO2 emission values. Therefore, the results indicate that the artificial neural network provides reliable estimates for the evaluation of FCO2 from data of the soil's physical and chemical attributes and describes the spatial variability of FCO2 in sugarcane fields, thereby contributing to the reduction of uncertainties associated with FCO2 accountings in these areas.