The invention discloses a one-dimensional synthetic aperture radiometer sea surface wind speed inversion method based on deep learning. The method comprises the following steps of obtaining sea surface temperature, sea water salinity, sea surface relative wind direction, incident angle, atmospheric water vapor content and cloud liquid water content, inputting the sea surface temperature, the sea water salinity, the sea surface relative wind direction, the incident angle, the atmospheric water vapor content and the cloud liquid water content into a radiation transmission forward model to obtaina simulated brightness temperature, and inputting the sea surface temperature, the sea water salinity, the sea surface relative wind direction, the incident angle, the atmospheric water vapor content, the cloud liquid water content and the simulated brightness temperature into a deep learning inversion model constructed based on a convolutional neural network to obtain the sea surface wind speed.The inversion precision is improved, and a method is provided for the one-dimensional synthetic aperture microwave radiometer to invert the sea surface wind speed.