Abstract
Current study results on artificial in telligence have been published. According to news originating from Adelaide, Aus tralia, by NewsRx correspondents, research stated, "The advent of satellite-born e machine learning hardware accelerators has enabled the onboard processing of p ayload data using machine learning techniques such as convolutional neural netwo rks (CNNs)." Funders for this research include Smartsat Crc. Our news journalists obtained a quote from the research from University of Adela ide: "A notable example is using a CNN to detect the presence of clouds in the m ultispectral data captured on Earth observation (EO) missions, whereby only clea r sky data are downlinked to conserve bandwidth. However, prior to deployment, n ew missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missio ns will underperform when deployed to process the data on the new missions. This underperformance stems from the domain gap, i.e., differences in the underlying distributions of the data generated by the different sensors in previous and fu ture missions. In this paper, we address the domain gap problem in the context o f onboard multispectral cloud detection."
NETL
NSTL