Restoration of Missing Patterns on Satellite Infrared Sea Surface Temperature Images Due to Cloud Coverage Using Deep Generative Inpainting Network
| Autor: | Young-Jin Choi, Song-Hee Kang, Jae Young Choi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
restoration
010504 meteorology & atmospheric sciences Computer science Inpainting Ocean Engineering Cloud computing 02 engineering and technology 01 natural sciences lcsh:Oceanography loss of sea surface temperature lcsh:VM1-989 sea surface temperature NOAA-19 infrared data deep generative adversarial network Satellite image 0202 electrical engineering electronic engineering information engineering daily-averaged SST Preprocessor lcsh:GC1-1581 0105 earth and related environmental sciences Water Science and Technology Civil and Structural Engineering 020203 distributed computing business.industry lcsh:Naval architecture. Shipbuilding. Marine engineering Pattern recognition Sea surface temperature Satellite Artificial intelligence business Generative grammar Interpolation |
| Zdroj: | Journal of Marine Science and Engineering Volume 9 Issue 3 Journal of Marine Science and Engineering, Vol 9, Iss 310, p 310 (2021) |
| ISSN: | 2077-1312 |
| DOI: | 10.3390/jmse9030310 |
| Popis: | In this paper, we propose a novel deep generative inpainting network (GIN) trained under the framework of generative adversarial learning, which is optimized for the restoration of cloud-disturbed satellite sea surface temperature (SST) imagery. The proposed GIN architecture can achieve accurate and fast restoration results. The proposed GIN consists of rough and fine reconstruction stages to promote the details and textures of missing (clouded) regions in SST images. We also propose a nov el preprocessing strategy that replaces the land areas with the average value of daily oceanic surface temperatures for improving restoration accuracy. To learn the proposed GIN, we developed a novel approach that combines multiple loss functions well suited for improving the restoration quality over missing SST information. Our results show that the difference in temperature between restored and actual satellite image data was no larger than 0.7 °C in monthly average values, which suggests excellent resilience against the missing sea surface temperature data. The proposed GIN has a faster restoration time and is feasible for real-time ocean-related applications. Furthermore, the computational cost of restoring SST images is much lower than the popular interpolation methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|