학술논문
Reconstruction of Sea Surface Temperature under Clouds using Masked Autoencoders
Document Type
Conference
Source
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2023 - 2023 IEEE International. :1076-1079 Jul, 2023
Subject
Language
ISSN
2153-7003
Abstract
This paper presents a methodology for reconstructing high-spatial-resolution sea surface temperature (SST) fields under cloud cover using masked autoencoders (MAE). The MAE model is trained on high-resolution SST maps from the ECCO forward simulation, LLC4320, and reconstructs missing data by masking out a portion of the input pixels. The impact of masking ratios and methods, as well as network architecture variations, is investigated. Preliminary results show that MAE can reconstruct global SST under a random 80% mask to within 0.3°C root mean squared error (RMSE). Applying this methodology to SST data with significant cloud contamination can enhance dataset quality, uncovering details hidden by clouds and expanding the use of high-resolution SST images.