Mr. Hirahara of Iiyama Laboratory, Kyoto University made an oral presentation titled “Denoising and Inpainting of Sea Surface Temperature Image with Adaptive Physical Model Loss” at ACPR 2019, the international conference on pattern recognition held in Auckland, New Zealand.

This research proposes a new approach for meteorology; estimating sea surface temperatures (SSTs) by using deep learning. SSTs are essential information for ocean-related industries but are hard to measure.