Disk2Planet

Paper: Mao, S., Dong, R., Yi, K.M., Lu, L., Wang, S. and Perdikaris, P., 2024. Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems. arXiv preprint arXiv:2409.17228.

Dataset

Dataset on https://huggingface.co

Package dependencies

Please refer to requirements.txt and requirements-macos.txt.

Usage

Basic

Please refer to onet_disk2D/cma_opt.py for solving inverse problem.

Advanced

Please refer to cma_group_submit.sh and guild.yml for running multiple instances in parallel.

Acknowledge

We thank Jaehan Bae, Xuening Bai, Pablo Ben{'\i}tez-Llambay, Shengze Cai, Miles Cranmer, Bin Dong, Scott Field, Jeffrey Fung, Xiaotian Gao, Jiequn Han, Pinghui Huang, Pengzhan Jin, Xiaowei Jin, Hui Li, Tie-Yan Liu, Zhiping Mao, Chris Ormel, Wenlei Shi, Karun Thanjavur, Yiwei Wang, Yinhao Wu, Zhenghao Xu, Minhao Zhang, Wei Zhu for help and useful discussions in the project.

This project heavily relies on Guild.ai for experiment tracking. We sincerely thank the Guild.ai team for publishing such wonderful software and providing maintenance.

S.M. and R.D. are supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Alfred P. Sloan Foundation. S.M. and R.D. acknowledge the support of the Government of Canada's New Frontiers in Research Fund (NFRF), [NFRFE-2022-00159]. This research was enabled in part by support provided by the Digital Research Alliance of Canada \url{alliance.can.ca}.