Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 27, 2026Open Access

Identifying Exoplanets with Deep Learning VI. Enhancing neural network mitigation of stellar activity RV signals with additional metrics

View Full Paper
Ask AI
Bookmark
Share

Authors

NMNaomi McWilliamZBZ. de BeursAVAndrew Vanderburg

Discussion

Loading...

Member takes

Overview

Demonstrates improved radial velocity predictions in exoplanet detection using deep learning and stellar activity metrics.

Key Points

  • The aim is to enhance the predictive power of neural networks in measuring exoplanet masses by addressing stellar activity noise.
  • Trained a neural network on six years of HARPS-N solar data.
  • Incorporated additional stellar activity parameters like chromatic CCFs and spectral indicators.
  • Compared the neural network's performance using different input parameters.
  • Achieved a reduction in RV scatter from 147.1 cm/s to 93.3 cm/s in a test set.
  • Certain parameters improved predictive ability, while others did not significantly enhance results.
  • Identified effective tracers for supergranulation to mitigate RV jitter.

Cite This Study

McWilliam et al. (2026) studied this question.

synapsesocial.com/papers/69a1344fed1d949a99abe0eahttps://doi.org/10.3847/1538-3881/ae45fd
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Improving Earth-like planet detection in radial velocity using deep learning2024 · 2 citations
  2. 2Improving Earth-like planet detection in radial velocity using deep learning2024 · 12 citations
  3. 3Mitigating stellar radial velocity jitter using orthogonal activity indices and a time-aware neural network2026
  4. 4Investigating stellar activity through eight years of Sun-as-a-star observations2024
  5. 5Investigating stellar activity through eight years of Sun-as-a-star observations2024 · 21 citations