Estimation of daytime all-sky sea surface temperature from Himawari-8 based on multilayer stacking machine learning

Abstract

The Himawari-8 satellite has the capability to rapidly retrieve sea surface temperature (SST) data at a high frequency of 10 min, demonstrating significant potential for various scientific applications. However, the presence of cloud often results in missing SST data at cloud locations, or can reduce the accuracy of retrieved SST. In contrast to the method of reconstructing missing SST data, this study focuses on exploring the potential of inverting SST under all-sky conditions. This study proposes a three-layer stacked machine learning model (TLSM), specifically designed for SST under all-sky conditions. The model integrates cloud properties into its input features to effectively account for the influence of cloud cover. Validation using 30 % match-up pairs generated an overall root mean square error (RMSE) of 0.71 °C, a Bias of −0.01 °C, and an R2 of 0.91 based on 6383 samples. For clear-sky conditions, TLSM demonstrates a noteworthy enhancement in SST inversion accuracy (R2 = 0.98, RMSE=0.35 °C) compared to the official SST product (R2 = 0.86, RMSE=0.88 °C). In cases of optically thin clouds and clouds with low cloud top pressure, TLSM exhibits commendable proficiency in the inversion of SST. The Bias and RMSE for these cloud types indicate better performance compared to the official clear-sky SST data. While including cloud samples may reduce the overall accuracy of the TLSM, it substantially enhances the spatial coverage of the inverted SST. Considering the performance for each cloud type, TLSM may serve as an alternative approach for SST retrieve under thin clouds.

Keywords

• SST inversion
• All-sky
• Stacked machine learning
• Himawari-8 satellite
• Cloudy SST