Source term estimation based on environmental monitoring data is a key method for obtaining source information, which is required by the emergency response system. This study investigates the applicability of deep feedforward neural network (DFNN) for source inversion. Twenty thousand sets of simulated data containing I-131 release rate, meteorological information, and simulated radioactive concentration are generated based on radionuclide atmospheric dispersion codes RADC. These are used to train and test a DFNN. The influence of key network hyperparameters is studied. The results show that the average prediction error of DFNN is 2.24%, and that over 80% of prediction errors are less than 2.0%. The Bayesian MCMC algorithm is used to analyze the prediction uncertainty of DFNN when there are uncertainties in the input parameters. The confidence interval and risk curve are likely to provide more reliable source-term information for nuclear accident emergency response and decision-making.