LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909505229422592 |
|---|---|
| author | Viaña, Javier Hwang, Kyu-Ha de Beurs, Zoë Yee, Jennifer C. Vanderburg, Andrew Albrow, Michael D. Chung, Sun-Ju Gould, Andrew Han, Cheongho Jung, Youn Kil Ryu, Yoon-Hyun Shin, In-Gu Shvartzvald, Yossi Yang, Hongjing Zang, Weicheng Cha, Sang-Mok Kim, Dong-Jin Kim, Seung-Lee Lee, Chung-Uk Lee, Dong-Joo Lee, Yongseok Park, Byeong-Gon Pogge, Richard W. |
| author_facet | Viaña, Javier Hwang, Kyu-Ha de Beurs, Zoë Yee, Jennifer C. Vanderburg, Andrew Albrow, Michael D. Chung, Sun-Ju Gould, Andrew Han, Cheongho Jung, Youn Kil Ryu, Yoon-Hyun Shin, In-Gu Shvartzvald, Yossi Yang, Hongjing Zang, Weicheng Cha, Sang-Mok Kim, Dong-Jin Kim, Seung-Lee Lee, Chung-Uk Lee, Dong-Joo Lee, Yongseok Park, Byeong-Gon Pogge, Richard W. |
| contents | Traditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time-consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale for widespread exoplanet detection, ultimately hindering discovery rates. To address the limits of traditional microlensing event vetting, we have developed LensNet, a machine learning pipeline specifically designed to distinguish legitimate microlensing events from false positives caused by instrumental artifacts, such as pixel bleed trails and diffraction spikes. Our system operates in conjunction with a preliminary algorithm that detects increasing trends in flux. These flagged instances are then passed to LensNet for further classification, allowing for timely alerts and follow-up observations. Tailored for the multi-observatory setup of the Korea Microlensing Telescope Network (KMTNet) and trained on a rich dataset of manually classified events, LensNet is optimized for early detection and warning of microlensing occurrences, enabling astronomers to organize follow-up observations promptly. The internal model of the pipeline employs a multi-branch Recurrent Neural Network (RNN) architecture that evaluates time-series flux data with contextual information, including sky background, the full width at half maximum of the target star, flux errors, PSF quality flags, and air mass for each observation. We demonstrate a classification accuracy above 87.5%, and anticipate further improvements as we expand our training set and continue to refine the algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network Viaña, Javier Hwang, Kyu-Ha de Beurs, Zoë Yee, Jennifer C. Vanderburg, Andrew Albrow, Michael D. Chung, Sun-Ju Gould, Andrew Han, Cheongho Jung, Youn Kil Ryu, Yoon-Hyun Shin, In-Gu Shvartzvald, Yossi Yang, Hongjing Zang, Weicheng Cha, Sang-Mok Kim, Dong-Jin Kim, Seung-Lee Lee, Chung-Uk Lee, Dong-Joo Lee, Yongseok Park, Byeong-Gon Pogge, Richard W. Instrumentation and Methods for Astrophysics Earth and Planetary Astrophysics Astrophysics of Galaxies Artificial Intelligence 85-08 J.2 Traditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time-consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale for widespread exoplanet detection, ultimately hindering discovery rates. To address the limits of traditional microlensing event vetting, we have developed LensNet, a machine learning pipeline specifically designed to distinguish legitimate microlensing events from false positives caused by instrumental artifacts, such as pixel bleed trails and diffraction spikes. Our system operates in conjunction with a preliminary algorithm that detects increasing trends in flux. These flagged instances are then passed to LensNet for further classification, allowing for timely alerts and follow-up observations. Tailored for the multi-observatory setup of the Korea Microlensing Telescope Network (KMTNet) and trained on a rich dataset of manually classified events, LensNet is optimized for early detection and warning of microlensing occurrences, enabling astronomers to organize follow-up observations promptly. The internal model of the pipeline employs a multi-branch Recurrent Neural Network (RNN) architecture that evaluates time-series flux data with contextual information, including sky background, the full width at half maximum of the target star, flux errors, PSF quality flags, and air mass for each observation. We demonstrate a classification accuracy above 87.5%, and anticipate further improvements as we expand our training set and continue to refine the algorithm. |
| title | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| topic | Instrumentation and Methods for Astrophysics Earth and Planetary Astrophysics Astrophysics of Galaxies Artificial Intelligence 85-08 J.2 |
| url | https://arxiv.org/abs/2501.06293 |