Details

Autor(en) / Beteiligte

• Yin, Jifu
• Zhan, Xiwu
• Barlage, Michael
• Liu, Jicheng
• Meng, Huan
• Ferraro, Ralph R.

Titel

Refinement of NOAA AMSR-2 Soil Moisture Data Product—Part 2: Development With the Optimal Machine Learning Model

Ist Teil von

• IEEE transactions on geoscience and remote sensing, 2023, Vol.61, p.1-11

Ort / Verlag

New York: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)

Erscheinungsjahr

2023

Quelle

IEEE Electronic Library Online

Beschreibungen/Notizen

• Advanced Microwave Scanning Radiometer-2 (AMSR2) is a successor of AMSR for Earth-Observation System (AMSR-E), while the third generation of AMSR (AMSR3) will be launched in the near future. The AMSR2 soil moisture (SM) product is also an important component of the SM operational products system (SMOPS) datasets that are operationally produced by National Oceanic and Atmospheric Administration (NOAA). The refinement of the NOAA AMSR2 SM data product can not only benefit the past AMSR-E and the upcoming AMSR3 but also improve the SMOPS data quality. In this second article of the two-part series, the extreme gradient boosting (XGB) model was trained using the AMSR2 6.925-, 10.65-, 18.7-, and 36.5-GHz brightness temperature (Tb) measurements in dual polarizations, ancillary maps, and the vegetation index datasets and in turn used to predict the daily global AMSR2 SM retrievals from 2012 to 2021. Validation results show that the refined AMSR2 SM retrievals (AMSRr) show an overwhelming advantage in data accuracy over the currently operational AMSR2 (AMSRc) product. Compared to the AMSRc, the developed AMSRr presents a significant improvement on data availability. Results also indicate that the refined AMSR2 datasets are comparable with the latest version SM active passive (SMAP) SM product. Based on this study, higher quality AMSRr SM data product will be operationally produced in the NOAA and will eventually benefit the NOAA SMOPS blended SM product and its users.