Translator Disclaimer
Presentation
12 September 2019 Preparing weather and environment satellite big data for AI (Conference Presentation)
Author Affiliations +
Abstract
According to World Meteorological Organization (WMO) Space Program Observing Systems Capability Analysis and Review Tool (OSCAR) web site https://www.wmo-sat.info/oscar/satellites more than 727 entries are listed to document the past, current and future satellites for meteorological and earth observation missions. With most of the satellite carries multiple sensors it’s estimated that a few thousands of sensors have made, are making and will make remote sensing big data in the order of thousands of petabyte. These old, new, and future heterogeneous weather and environmental information-rich observations, coupled with other airborne and ground-based remote sensing, in-situ sensors, and model data are overwhelming our current capability to archive them, let alone, the attempt to use them. In this presentation, we are to leverage this phenomenal volume of complex data by exploring the possibility and concept of preparing for unified data structure and architecture suitable for the effective and optimal use of the advanced machine and deep learning artificial intelligence (AI). We’ll conclude with the potential of combining weather and environment big data with sophisticated mathematical algorithms, high-performance computing power, and deep learning analytics, that one can harness significant investments in the data collection and to demonstrate a benefit that outweigh the costs in advancing our capability in weather forecasting, environment monitoring, and climate study.
Conference Presentation
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hung-Lung Allen Huang "Preparing weather and environment satellite big data for AI (Conference Presentation)", Proc. SPIE 11127, Earth Observing Systems XXIV, 1112709 (12 September 2019); https://doi.org/10.1117/12.2528047
PROCEEDINGS
PRESENTATION


SHARE
Advertisement
Advertisement
Back to Top