The paper investigates the retrieval of sea surface barometric pressure under clear sky by passive measurements. Several linear and nonlinear statistical algorithms are presented and the passive microwave measurements from the Advanced Technology Microwave Sounder (ATMS) on S-NPP satellite are used for the algorithm training and verification. The retrieval are assessed by evaluation of root mean square error (RMSE), with comparison with the reanalysis data of European Centre for Medium-Range Weather Forecasts (ECMWF). The validated results show that Support Vector Regression (SVR) has the best performance and the corresponding RMSE of sea surface pressure is 1.53mb. The accuracy is comparable with the other traditional in-situ methods, and satisfy the requirements for meteorological applications.