Rubber sheets are one of the primary products of natural rubber and are the main raw material in various rubber industries. The quality of a rubber sheet can be visually examined by holding it against clear light to inspect for any specks and impurities inside, but its moisture content is di±cult to evaluate based on a visual inspection and this might lead to unfair trading. Herein, we developed a rapid, robust and nondestructive near-infrared spectroscopy (NIRS)-based method for moisture content determination in rubber sheets. A set of 300 rubber sheets were divided into a calibration (200 samples) and prediction groups (100 samples). The calibration set was used to develop NIRS calibration equation using different calibration models, Partial Least Square Regression (PLSR), Least Square Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN). Among the models investigated, the ANN model with the first derivative of spectral preprocessing presented the best prediction with a coe±cient of determination (R2P) of 0.993, root mean square error of calibration (RMSEC) of 0.126% and root mean square error of prediction (RMSEP) of 0.179%. The results indicated that the proposed NIRS-ANN model will be able to reduce human error and provide a highly accurate estimate of the moisture content in a rubber sheet compared to traditional wet chemistry estimation methods according to AOAC standards.