BEIJING -- A group of Chinese researchers have designed a Generalized Data Completion Model (GDCM) applicable to multi-source remote sensing data in aiming to solve the missing measurement caused by satellite orbit coverage gaps and cloud cover, according to the Chinese Academy of Sciences (CAS).

Ocean remote sensing data is crucial for understanding the global climate system. Due to satellite orbital coverage gaps and cloud cover, satellite ocean remote sensing products have exhibited significant data gaps.

Based on deep learning, researchers from the Institute of Oceanology of the CAS and the University of the CAS reconstructed gap-free and cloud-free key oceanic variables such as sea surface temperature, wind speed, water vapor, cloud liquid water and precipitation rate.

The GDCM model effectively leveraged spatio-temporal information within remote sensing data to fill in missing regions accurately, according to the research article published in the journal Remote Sensing of Environment.

To enable the model to capture enough data for the requirements of dynamical change patterns, the researchers used seven consecutive days of observation data as inputs to improve the model's data-completion ability, significantly enhancing the handling of data missing due to cloud cover.

The study provided a generalized new solution to the problem of absent ocean data at different resolutions -- thereby contributing to more comprehensive and supportive ocean science research and related applications.