The invention belongs to the technical field of tobacco production, and particularly relates to a hyperspectral field tobacco leaf total sugar content prediction method and system based on an unmanned aerial vehicle. The method comprises the following steps of: acquiring field tobacco leaf hyperspectral image data in real time through an unmanned aerial vehicle; carrying out coordinate loading on the hyperspectral image data, and extracting and processing a corresponding original spectral curve; obtaining a field sample tobacco leaf total sugar content estimation value, and constructing a field tobacco leaf total sugar content prediction model according to the field sample tobacco leaf total sugar content estimation value and the spectral characteristic curve; and generating total sugar content prediction data corresponding to field tobacco leaves. For large-area field tobacco leaves, compared with most traditional indoor tobacco leaf observation and research, the total sugar content of the tobacco leaves can be estimated only by obtaining the hyperspectral data of the tobacco leaves and utilizing the constructed model, the method for constructing the model is simple in calculation, high in practicability and rapid, and large-area damage to tobacco plants is reduced.