Traditional methods of well surveillance, mainly test separator units, suffer from their inherent constraints, including expensive costs. The objective of this approach is to classify the oil samples taken from individual wells by source and type. The novelties of this work are utilizing the applied aspects of spectroscopy in petroleum upstream engineering, replacing traditional test methods, improving the confidence of tests, and recognizing multisource streams. The weighed sum method was used to correlate the Fourier transform infrared (FTIR) spectra taken from samples of Iranian offshore oil wells. The experimental results and the field data revealed that the present approach is appropriate for precocious, quick, and reliable surveillance of individual oil wells located in an oil field. The model was supported by thermogravimetric experiments and has accurately predicted the productivity of oil wells with respect to current expensive techniques since 2010.