Remote sensing based on Remote Piloted Aircraft Systems (RPAS) has proved valuable for monitoring agronomic parameters in precision agriculture. This research aimed to develop predictive models based on machine learning to estimate indirect nitrogen levels (Narea) and grain yield in irrigated rice. During the five phenological stages of cultivation, a Sequoia® camera aboard the Phantom 4® Pro platform acquired the multispectral images. In addition to the spectral bands, 11 vegetation indices were taken as predictors of the response variables (Narea and grain yield). Spearman's correlation coefficient (p) analyzed the ideal monitoring window and selected the model variables. The Multi-Layer Perceptron (MLP) algorithm adjusted the predictive models that had their performance evaluated in training and testing. The results obtained by the Spearman correlation indicate that the ideal window for monitoring rice by RPAS, for both response variables, occurs at the beginning of the reproduction phase (R1). MLP generated a more accurate model for Narea, demonstrated by Pearson's correlation between predicted and observed values (0.82 and 0.71) and mean absolute error (MAE) of 9.47 and 10.89. Grain yield models show good MLP at all stages and excellent accuracy. In this way, our results reinforce the excellent efficiency of the combination of remote sensing via RPAS and machine learning in applications aimed at precision agriculture, serving as a useful tool for managing production and evaluating grain yield in irrigated rice fields.