2021 Fiscal Year Research-status Report
Combining Collective and Artificial Intelligence to Understand the Early Universe
| Project/Area Number |
20K14464
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
HARTWIG Tilman 東京大学, 大学院理学系研究科(理学部), 助教 (00843434)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | Artificial Intelligence / Machine Learning / Milky Way / Stellar Parameters |
|---|
| Outline of Annual Research Achievements |
We have weekly online meetings to discuss the status and updates of the Subaru PFS analysis pipeline for Galactic Archaeology. We have centralized the code development for this project in a common git repository. With the updated software, we have calculated the expected signal-to-noise ratio of the future observations to estimate down to which magnitude we are sensitive to the chemical composition of stars.
Together with the Subaru PFS collaboration, we wrote the SSP for the instrument and are including feedback from an external committee.
We have created a regular grid of synthetic spectra together with Dr. Mohammad Mardini (UTokyo). We will confirm the validity of these spectra together with Evan Kirby (CalTech) and Laszlo Dobos (JHU). Moreover, the first components of the Subaru PFS spectrogram were delivered to Hawaii and are currently being tested.
The Covid restrictions do not allow us to organize public lectures or other forms of citizen science events, as originally planned. If the Covid situation improves this year, we plan to follow our original plan. Otherwise, we plan to host at least one data science challenge on Kaggle.com, a popular website for people who want to learn and practice AI.
|
| Current Status of Research Progress |
Current Status of Research Progress
3: Progress in research has been slightly delayed.
Reason
The global Covid-19 pandemic impacted our project. International travel is restricted, and collaborators could not come to Tokyo as planned. We are trying to continue the discussions online as much as possible, but this way of communication is not ideal, and the progress of the project is therefore unfortunately slower than expected.
One pillar of this project should be Collective Intelligence in the form of public lectures and citizen science. Due to the pandemic, this was not possible until now (see future plans).
|
| Strategy for Future Research Activity |
If the Covid situation improves this year, we plan to follow our original plan for public lectures. Otherwise, we plan to host at least one data science challenge on Kaggle.com, a popular website for people who want to learn and practice AI. Formulating our machine learning problem as Kaggle challenge will have a similar impact as our original plan: 1) a diverse group of users can explore our astronomical data and learn machine learning. 2) we will have new scientific inspirations of how to optimally analyse the PFS data from citizen scientists.
We will create a realistic distribution of synthetic spectra. This is important as training set for any machine learning pipeline.
We will obtain the first test observations from the Subaru PFS engineering runs. This information will help us to optimize the analysis pipeline by focusing on realistic ranges for magnitudes and metallicities.
|
| Causes of Carryover |
Due to the global Covid-19 pandemic, several items could not be executed as originally planned. Especially international travel was restricted and the money from this grant could not be spent on travel, international collaborations, and conferences. Moreover, we were not able to organize public lectures on AI, as originally planned.
The remaining money will be spent on: 1) Kaggle competition:
200,000JPY 2) Travel to collaboration meeting: 500,000JPY 3) Publication charges: 300,000JPY 4) Books hardware & Miscellaneous: 52,000JPY
|
