Unsupervised domain adaptation for Global Precipitation Measurement satellite constellation using Cycle Generative Adversarial Nets

• Published in: Environmental Data Science Vol. 1
• Main Authors: Sambath, Vibolroth, Viltard, Nicolas, Barthès, Laurent, Martini, Audrey, Mallet, Cécile
• Format: Journal Article
• Language: English
• Published: Cambridge University Press 2022
• Subjects: Earth Sciences; Meteorology; Microwave brightness temperature; rain retrieval; Sciences of the Universe; transfer learning; unsupervised domain adaptation; transfer learning; Microwave brightness temperature; rain retrieval; unsupervised domain adaptation
• ISSN: 2634-4602; 2634-4602
• DOI: 10.1017/eds.2022.16

Artificial intelligence has provided many breakthroughs in the field of computer vision. The fully convolutional networks U-Net in particular have provided very promising results in the problem of retrieving rain rates from space-borne observations, a challenge that has persisted over the past few decades. The rain intensity is estimated from the measurement of the brightness temperatures on different microwave channels. However, these channels are slightly different depending on the satellite. In the case where a retrieval model has been developed from a single satellite, it may be advantageous to use domain adaptation methods in order to make this model compatible with all the satellites of the constellation. In this proposed feasibility study, a Cycle Generative Adversarial Nets model is used for adapting one set of brightness temperature channels to another set. Results of a toy experiment show that this method is able to provide qualitatively good precipitation structure but still could be improved in terms of precision.