| Name: | Nitya Pandey |
| Affiliation: | University of Chile |
| Conference ID : | ASI2024_508 |
| Title : | Deep Learning CNN for Ground-Based TNO Detection: Bridging AI and DEEP survey for Trans-Neptunian Object Revelation |
| Authors : | Miss Nitya Pandey 1
Dr. Cesar Fuentes 2
|
| Authors Affiliation: | 1 Miss Nitya Pandey (Department of Astronomy, University of Chile, Santiago, 7591245, Chile)
2 Dr. Cesar Fuentes (Department of Astronomy, University of Chile, Santiago, 7591245, Chile) |
| Mode of Presentation: | Poster |
| Abstract Category : | Sun, Solar System, Exoplanets, and Astrobiology |
| Abstract : | The DECam Ecliptic Exploration Project (DEEP), a multiyear survey of the trans-Neptunian region, provides a unique window into the planetesimals responsible for our solar system's formation. Utilizing the shift-and-stack algorithm, the DEEP search identified and characterized 110 new Trans-Neptunian objects. With a fresh perspective, our study presents an alternative approach to studying these objects.
We present an AI-based moving object detection technique. Instead of following the traditional shift and stack, we perform simple stacking on the same DEEP's single-field night images using different statistics. The algorithm comprises two key components. The first involves pre-processing, which encompasses six major steps ranging from background subtraction to the combination of images using different statistics. The processes effectively generate discernible trails in the final combined image. Subsequently, these images are fed into an AI framework, where the YOLOv8 deep learning convolutional neural network is trained to identify moving object trails out of noise.
Notably, the algorithm's strength lies in its ability to expedited analysis of large datasets while minimizing false positives. Moreover, our aim is to enable the detection of faint TNOs using the DEEP results as benchmark magnitude limit of R ̴ 26.2 and achieve real-time moving object detection as soon as the data becomes available. Our current single image detection depth is R ̴ 25.
In this presentation, I will delve into the key methods used in this innovative technique and discuss some of the challenges faced during its development, with a focus on the role of AI in enabling fast and efficient moving object detection in the Trans-Neptunian region. Also, I will discuss how this can be implemented in deep drilling fields from LSST and other wide field surveys, possibly enhancing the yield of new Solar System objects, particularly for those that exhibit a sky motion unsuitable for deep drilling.
|
