Soil moisture and gaseous N-flux (N2O, N-2) dynamics in Costa Rican coffee plantations were successively simulated using a mechanistic model (PASTIS) and two process-based models (NGAS and NOE). Two fertilized (250 kg N ha(-1) y(-1)) coffee plantations were considered, namely a monoculture and a system shaded by the N-2 fixing legume species Inga densiflora. In situ N2O fluxes were previously measured in these plantations. NGAS and NOE used specific microbial activities for the soils. To parameterize NGAS, we estimated N mineralization via in situ incubations and the contribution of heterotrophic soil respiration to total soil respiration. Potential denitrification rates and the proportion of denitrified N emitted as N2O were measured in the laboratory to define the values of NOE parameters, as well as nitrification rates and related N2O production rates for parameterizing both models. Soil moisture and both NGAS and NOE N2O fluxes were best modelled on an hourly time step. Soil moisture dynamics were satisfactorily simulated by PASTIS. Simulated N2O fluxes by both NGAS and NOE (3.2 and 2.1 kg N ha(-1) y(-1) for NGAS; 7.1 and 3.7 kg N ha(-1) y(-1) for NOE, for the monoculture and shaded plantations respectively) were within a factor of about 2 of the observed annual fluxes (4.3 and 5.8 kg N ha(-1) y(-1), for the monoculture and shaded plantations respectively). Statistical indicators of association and coincidence between simulated and measured values were satisfactory for both models. Nevertheless, the two models differed greatly in describing the nitrification and denitrification processes. Some of the algorithms in the model NGAS were apparently not applicable to these tropical acidic Andosols. Therefore, more detailed information about microbial processes in different agroecosystems would be needed, notably if process-oriented models were to be used for testing strategies for mitigating N2O emissions. (C) 2009 Elsevier Ltd. All rights reserved.