Follow the water: finding water, snow, and clouds on terrestrial exoplanets with photometry and machine learning
Bibliographic record
Abstract
ABSTRACT All life on Earth needs water. NASA’s quest to follow the water links water to the search for life in the cosmos. Telescopes like the James Webb Space Telescope and mission concepts like HabEx, LUVOIR, and Origins are designed to characterize rocky exoplanets spectroscopically. However, spectroscopy remains time-intensive, and therefore, initial characterization is critical to prioritization of targets. Here, we study machine learning as a tool to assess water’s existence through broad-band filter reflected photometric flux on Earth-like exoplanets in three forms: seawater, water-clouds, and snow; based on 53 130 spectra of cold, Earth-like planets with six major surfaces. XGBoost, a well-known machine-learning algorithm, achieves over 90 per cent balanced accuracy in detecting the existence of snow or clouds for S/N ≳ 20, and 70 per cent for liquid seawater for S/N ≳ 30. Finally, we perform mock Bayesian analysis with Markov chain Monte Carlo with five filters identified to derive exact surface compositions to test for retrieval feasibility. The results show that the use of machine learning to identify water on the surface of exoplanets from broad-band filter photometry provides a promising initial characterization tool of water in different forms. Planned small and large telescope missions could use this to aid their prioritization of targets for time-intense follow-up observations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".