摘要：Sea surface temperature (SST) is an important geophysical parameter that is essential for studying global climate change. Although sea surface temperature can currently be obtained through a variety of sensors (MODIS, AVHRR, AMSR-E, AMSR2, WindSat, in situ sensors), the temperature values obtained by different sensors come from different ocean depths and different observation times, so different temperature products lack consistency. In addition, different thermal infrared temperature products have many invalid values due to the influence of clouds, and passive microwave temperature products have very low resolutions. These factors greatly limit the applications of ocean temperature products in practice. To overcome these shortcomings, this paper first took MODIS SST products as a reference benchmark and constructed a temperature depth and observation time correction model to correct the influences of the different sampling depths and observation times obtained by different sensors. Then, we built a reconstructed spatial model to overcome the effects of clouds, rainfall, and land interference that makes full use of the complementarities and advantages of SST data from different sensors. We applied these two models to generate a unique global 0.041 ∘ gridded monthly SST product covering the years 2002–2019. In this dataset, approximately 25 % of the invalid pixels in the original MODIS monthly images were effectively removed, and the accuracies of these reconstructed pixels were improved by more than 0.65 ∘ C compared to the accuracies of the original pixels. The accuracy assessments indicate that the reconstructed dataset exhibits significant improvements and can be used for mesoscale ocean phenomenon analyses. The product will be of great use in research related to global change, disaster prevention, and mitigation and is available at https://doi.org/10.5281/zenodo.4419804 (Cao et al., 2021a).
