Deep Learning for Sea Surface Temperature Reconstruction under Cloud Occlusion
This provides improved SST reconstructions for oceanography and climate research, but is incremental as it applies an existing deep learning method to a known problem.
The paper tackled the problem of reconstructing sea surface temperature from satellite images with cloud gaps using a U-net convolutional neural network, achieving 50% lower root mean square errors compared to established gap-filling methods.
Sea Surface Temperature (SST) reconstructions from satellite images affected by cloud gaps have been extensively documented in the past three decades. Here we describe several Machine Learning models to fill the cloud-occluded areas starting from MODIS Aqua nighttime L3 images. To tackle this challenge, we employed a type of Convolutional Neural Network model (U-net) to reconstruct cloud-covered portions of satellite imagery while preserving the integrity of observed values in cloud-free areas. We demonstrate the outstanding precision of U-net with respect to available products done using OI interpolation algorithms. Our best-performing architecture show 50% lower root mean square errors over established gap-filling methods.