Tobacco leaf near infrared spectrum chemical component model optimization method based on transfer learning

The invention relates to a tobacco near infrared spectrum chemical component model optimization method based on transfer learning, belongs to the technical field of tobacco detection, and provides a tobacco near infrared spectrum chemical component model optimization method based on transfer learning on the basis of an existing near infrared spectrum tobacco detection model. In order to cope with the precision influence of the original model caused by the change of factors such as environment and climate, effective information in the broken leaf spectrum is migrated by utilizing a correlation-ratio migration learning method, the stability of a whole leaf spectrum measurement model is improved, and a brand new prediction model about the content of total sugar, reducing sugar, total plant alkaloid, potassium and chlorine is established. According to the optimization method, the workload consumed by resampling and modeling can be reduced, a more constant prediction model is established, the method can be used fo