The invention discloses a high-temporal-spatial-resolution surface
evapotranspiration remote sensing inversion method, and relates to the technical field of surface
evapotranspiration inversion. Comprising the following steps: making high and low spatial resolution surface reflectance
remote sensing samples, constructing a high super-resolution model, selecting
time sequence low-resolution surface reflectance
remote sensing data, carrying out super-resolution calculation on the
time sequence low-resolution surface reflectance remote
sensing data by using the super-resolution model, and carrying out super-resolution calculation on the
time sequence low-resolution surface reflectance remote
sensing data by taking the high spatial-
temporal resolution surface reflectance remote
sensing data as input. And carrying out surface resolution inversion based on the SEBAL model, taking an inversion result of the SEBAL model and part of meteorological data as input, carrying out surface
evapotranspiration inversion by using a
convolutional neural network, and outputting an inversion result. According to the method, the spatial resolution of the
satellite images with high
time resolution and low spatial resolution is greatly improved through the super-resolution technology, so that the
satellite images have high
time resolution and spatial resolution at the same time, and the problem that the
time resolution and the spatial resolution of input data required by continuous evapotranspiration remote sensing inversion are inconsistent is solved.