WATSON-Net: Vetting, Validation, and Analysis of Transits from Space Observations with Neural Networks
This provides a scalable automated tool for astronomers to prioritize exoplanet candidates, but it is incremental as it builds on existing deep learning approaches for this domain.
The paper tackles the problem of automating the vetting and validation of transiting exoplanet candidates from space missions like Kepler and TESS, presenting WATSON-Net, a neural network classifier that achieves a recall-at-precision of 0.99 of 0.903 for Kepler and precision of 0.93 with recall of 0.76 for TESS, ranking competitively with state-of-the-art tools.
Context. As the number of detected transiting exoplanet candidates continues to grow, the need for robust and scalable automated tools to prioritize or validate them has become increasingly critical. Among the most promising solutions, deep learning models offer the ability to interpret complex diagnostic metrics traditionally used in the vetting process. Aims. In this work, we present WATSON-Net, a new open-source neural network classifier and data preparation package designed to compete with current state-of-the-art tools for vetting and validation of transiting exoplanet signals from space-based missions. Methods. Trained on Kepler Q1-Q17 DR25 data using 10-fold cross-validation, WATSON-Net produces ten independent models, each evaluated on dedicated validation and test sets. The ten models are calibrated and prepared to be extensible for TESS data by standardizing the input pipeline, allowing for performance assessment across different space missions. Results. For Kepler targets, WATSON-Net achieves a recall-at-precision of 0.99 (R@P0.99) of 0.903, ranking second, with only the ExoMiner network performing better (R@P0.99 = 0.936). For TESS signals, WATSON-Net emerges as the best-performing non-fine-tuned machine learning classifier, achieving a precision of 0.93 and a recall of 0.76 on a test set comprising confirmed planets and false positives. Both the model and its data preparation tools are publicly available in the dearwatson Python package, fully open-source and integrated into the vetting engine of the SHERLOCK pipeline.