Recently, there has been growing interest and attention towards daytime radiative cooling. This cooling technology is considered a potentially significant alternative to traditional cooling methods because of its neither energy consumption nor harmful gas emission during operation. In this paper, a daytime radiative cooling emitter (DRCE) consisting of polydimethylsiloxane, silicon dioxide, and aluminum nitride from top to bottom on a silver-silicon substrate was designed by a machine learning method (MLM) and genetic algorithm to achieve daytime radiative cooling. The optimal DRCE had 94.43% average total hemispherical emissivity in the atmospheric window wavelength band and 98.25% average total hemispherical reflectivity in the solar radiation wavelength band. When the ambient temperature was 30°C, and the power of solar radiation was about 900W/m 2, the net cooling power of the optimal DRCE could achieve 140.38W/m 2. The steady-state temperature of that could be approximately 9.08°C lower than the ambient temperature. This paper provides a general research strategy for MLM-driven design of DRCE.