Séminaire Doctorants / Seminar PhD students |
| « LyAl-Net: A high-efficiency Lyman-Alpha forest simulation with neural network » |
|
Nai Boonkongkird |
|
LyAl-Net, a machine learning approach based on the U-net architecture,
to emulate the intergalactic medium physics of the Lyman-alpha forest in cosmological simulations. This approach provides a cheap and efficient way to simulate the Lyman-alpha forest and was tested with one and two-point statistics of emulated fields in different scenarios. Results show that this method accurately predicts the mean transmission of the Lyman-alpha forest, which is important for future QSO surveys. This approach has potential applications in the exploitation of upcoming cosmological surveys, such as WEAVE-QSO. |
|
vendredi 17 février 2023 - 16:00 Salle des séminaires Évry Schatzman, Institut d'Astrophysique |
| Page web du Séminaire / Seminar's webpage |