Sea Surface Temperature Estimation from Satellite Observations by Ensemble Learning

We propose a machine learning based method for sea surface temperature (SST) estimation and cloud detection in satellite data. To deal with estimation errors due to thin cloud cover, our approach uses observations from spectral bands not directly related to SST prediction as explanatory variables. This approach allows for implicit estimation of cloud conditions, which improves the performance of SST regression. Experimental results show that our method outperforms existing methods.