Proceso implementado por inteligencia artificial para la detección de petróleo

La solución pretendida, resuelve el problema planteado al aportar un método que comprende el uso de una inteligencia artificial (IA) en conjunto con un dispositivo de espectroscopía láser portátil como un láser de cascada cuántica que permita realizar análisis in situ. The present invention discloses a method for predicting a percentage of oil that comprises collecting spectra from the soil by means of infrared spectroscopy; standardising the signals; reducing the information by analysing the principal components; analysing the components by means of a support vector machine (SVM) learning model; merging the spectral data with the information obtained from the SVM model; processing the resulting information by means of a machine learning model based on the method of partial least squares combined with discriminant analysis; and predicting the percentage of oil present in the analysed array using a multilayer neural network.