TRANSCENDENCE - A TRANSit Capture ENgine for DEtection and Neural network Characterization of Exoplanets

Although the search for exoplanets currently incorporates various computational methods, it still heavily relies on manual analysis of light curves, a process that is both time-intensive and demanding. Our research in the EXOWORLD project addresses these challenges by integrating advanced machine learning techniques, including convolutional, into the transit search process, combining them with recurrent networks to create a fully integrated machine learning-based transit detection and characterization pipeline. This approach reimagines transit search as a pattern recognition task, employing self-learning algorithms to efficiently process vast amounts of astronomical data. We aim to explore and apply a range of machine learning methods, establishing a foundation for comparison not only among these methods but also against traditional transit search techniques. This comparison is expected to focus on potential improvements in efficiency, accuracy, and computational demands. Although still in the early stages, our research aims to significantly enhance exoplanet detection methods, streamlining the process and building a framework for making new discoveries through light curve analysis.

In this context, we present TRANSCENDENCE, our machine learning-based pipeline, which has demonstrated the ability to identify exoplanets larger than 2 Earth radii consitently. Moreover, the pipeline is capable of detecting smaller planets, albeit with lower detection probabilities. One of TRANSCENDENCE's key strengths lies in its remarkably low false positive rate, which ranges between 5% and 10% of all identified transits. By significantly reducing the need for manual intervention and minimizing false positives, this pipeline has the potential to strongly immprove the efficiency of exoplanet detection and characterization.