Generation of Spatial-Seamless AMSR2 Land Surface Temperature in China During 2012–2020 Using a Deep Neural Network

Abstract

Land surface temperature (LST) reflects the cold and hot conditions of land surface and is one of the most important geophysical parameters in the study and research of land-atmosphere system. Passive microwave (PMW) is one of the primary techniques for obtaining spatially continuous LST at regional, continental, and global scales. However, there is orbital gap in the LST retrieved from PMW (PMW LST) due to the scanning scheme of PMW sensor, which limits the application of PMW LST, so it is necessary to proposed some methods to fill the orbital gap of PMW LST. In this study, a new orbital gap filling method based on deep neural network (DNN) was developed to address the issue of PMW LST orbital gaps. This method first established DNN model based on the nonlinear relationship between AMSR2 LST and 11 environmental variables, and then used the DNN model to generate a new spatially continuous LST product, namely DNN-LST, and finally used DNN-LST to fill the orbital gaps of AMSR2 LST to generate the daytime/nighttime spatially seamless gap-filled LST product (GF-LST) for China from 2012 to 2020. GF-LST can more correctly represent the spatiotemporal variation of surface temperature in China than AMSR2 LST because it has continuous spatial texture information and no obvious boundary reconstruction effect. After verifying the accuracy of GF-LST products through simulated gap region validation and in-situ validation, it can be found that: (1) DNN-LST in simulated gap regions showed high accuracy during the daytime and nighttime on July 15, 2012-2020, and the mean values of bias and RMSE compared with AMSR2 LST at day (night) were respectively -0.08K (-0.22K) and 1.89K (2.23K); (2) the accuracy of DNN-LST was the best in autumn (mean RMSE values of 1.43K at day, 1.89K at night) and the worst in winter (mean RMSE values of 2.35K at day, 2.36K at night), no matter during daytime or nighttime, in different seasons in 2015-2017; (3) the RMSE value of DNN-LST during nighttime was slightly higher than the RMSE value of DNN-LST during daytime; (4) the accuracy of DNN-LST was equivalent to AMSR2 LST, that is, the ubRMSE of DNN-LST and AMSR2 LST was all about 4K compared with In-situ LST, but the ubRMSE of DNN-LST was slightly lower than AMSR2 LST. The above accuracy validation analysis shows that DNN-LST has good robustness and good spatial consistency with AMSR2 LST and can be well used to fill the orbital gap of AMSR2 LST to generate spatial seamless GF-LST product.