NeurIPS 2024 Ariel Data Challenge: Characterisation of Exoplanetary Atmospheres Using a Data-Centric Approach

The characterization of exoplanetary atmospheres through spectral analysis is a complex challenge. The NeurIPS 2024 Ariel Data Challenge, in collaboration with the European Space Agency’s (ESA) Ariel mission, provided an opportunity to explore machine learning techniques for extracting atmospheric compositions from simulated spectral data.

In this work, we focus on a data-centric business approach, prioritizing generalization over competition-specific optimization. We briefly outline multiple experimental axes, including feature extraction, signal transformation, and heteroskedastic uncertainty modeling.

Our experiments demonstrate that uncertainty estimation plays a crucial role in the Gaussian Log-Likelihood (GLL) score, impacting performance by several percentage points. Despite improving the GLL score by 11%, our results highlight the inherent limitations of tabular modeling and feature engineering for this task, as well as the constraints of a business-driven approach within a Kaggle-style competition framework.

Our findings emphasize the trade-offs between model simplicity, interpretability, and generalization in astrophysical data analysis.

Jeremie Blanchard, Lisa Casino, Jordan Gierschendorf

Comments: 12 pages
Subjects: Machine Learning (cs.LG); Instrumentation and Methods for Astrophysics (astro-ph.IM)
Cite as: arXiv:2505.08940 [cs.LG] (or arXiv:2505.08940v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2505.08940
Focus to learn more
Submission history
From: Jérémie Blanchard Msc
[v1] Tue, 13 May 2025 20:09:22 UTC (2,974 KB)
https://arxiv.org/abs/2505.08940
Astrobiology,