EVALUATION OF THE NITROGEN SUBMODEL OF CERES-MAIZE FOLLOWING LEGUME GREEN MANURE INCORPORATION

Crop simulation models that accurately predict the availability of N from decomposing plant residues would provide a powerful tool for evaluating legume green manures as potential N sources for nonlegume crops. Using measured data from a series of field experiments conducted on an Oxisol in central Brazil. we conducted this study to test the N submodel of CERES-Maize for its ability to simulate N mineralization, nitrate leaching, and N uptake by maize (Zea Mays L.) following the incorporation of 10 different legume green manures. Legume or weed residue N at the time of incorporation varied from 25 to 300 kg ha-1 with C/N ratios varying from 13 to 37. Comparison of predicted and measured accumulation of inorganic N in uncropped soil showed that the model usually provided a realistic simulation of legume N release, although N release was overpredicted for some legumes. For all legumes, both simulated and measured data showed that about 60% of the organic N applied was recovered as inorganic N within 120 to 150 d after incorporation. To realistically simulate N availability when rainfall was excessive, we modified the model to account for delayed leaching due to nitrate retention in the subsoil. Nitrogen uptake by maize was generally overpredicted at high levels of available N. The N submodel was shown to realistically simulate legume N release, but further work is needed to determine the importance of subsoil nitrate retention in other soils and how best such retention might be described in the model.