In order to improve the efficiency and accuracy of obtaining atmospheric transmittance parameters in infrared radiation test, this study proposes an atmospheric transmittance solution model based on HO-RF algorithm. The model takes the key environmental factors such as temperature, humidity, operating distance and atmospheric pressure as input, and establishes a regression solution model based on the measured data, so as to realize the rapid and accurate solution of atmospheric transmittance. The simulation results show that compared with the traditional BP neural network and RF model, the proposed HO-RF model performs better in terms of solution accuracy. The root mean square error ( RMSE ) is reduced to 0.010745, the R2 value is 0.95877, and the mean absolute error ( MAE ) is 0.0080021. The model proposed in this study can effectively reduce the complexity of experimental operation. Compared with the traditional method, it has higher accuracy, stability and reliability, and improves the efficiency of infrared characteristic test of fighter aircraft, which has good practical application value.