Embedded Files
Current difficulties in Astronomy research
Current difficulties in Astronomy research
Difficulty 1: Data are too large to be handled.
Many future sky survey projects are in Petabyte (PB; 1024 TB) level.
With Machine Learning, we can greatly reduce the processing time of massive data.
Difficulty 2: Features are too complicated.
With the flood of observational data, not only the quantity but also the information is increasing as well. It is not easy to analyze the data with tranditional methods.
A spectral energy distribution (SED) comparison between AGNs and a dusty SFG (Cai et al. 2013). In the mid-IR wavelengths, AGN (type 1-3) and SFG (cold/warm dust, and SMM J2135-0102) have distinct differences in their SED. AKARI’s 9-band filters are suitable in distinguishing them.
E.g. There are 12,000 parameters in AKARI's data analysis.
Machine learning can handle complicated features effectively.
There are many kinds of Machine Learning algorithms suitable for Astronomy research
There are many kinds of Machine Learning algorithms suitable for Astronomy research
Neural Network
Random Forrest
Generative adversarial network(GAN)
Machine Learning is a trend of scientific research
Machine Learning is a trend of scientific research
join our group and do machine learning astronomy research with us!
join our group and do machine learning astronomy research with us!
Google Sites
Report abuse