Datasets and experimental results for "Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks"

This dataset contains the training data and experimental results (i.e. trained models and results on the test set) for the research paper “Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks” by T. D. Gebhard et al. which has been accepted for publication in Astronomy & Astrophysics. The corresponding Python code is available at github.com/timothygebhard/ml4ptp. Please note that all rights to the training datasets remain with the respective original authors: PyATMOS dataset: A. Chopra et al. (2023). “PyATMOS: A Scalable Grid of Hypothetical Planetary Atmospheres.” arXiv:2308.10624 [Data available from the Exoplanet Archive] Goyal-2020 dataset: J. Goyal et al. (2020). “A library of self-consistent simulated exoplanet atmospheres.” MNRAS, 498 (4).

DOI:10.1093/mnras/staa2300 [Data available via Google Drive] The authors have kindly given us permission to republish these datasets here in a format that can be easily loaded into a machine learning pipeline.