Asteroid shape inversion with light curves using deep learning

TL;DR

This paper introduces a deep learning approach for asteroid shape inversion from light curves, enabling faster and more accurate shape predictions, including concave features, validated on observational data.

Contribution

The authors develop a neural network-based method that directly maps photometric data to 3D asteroid shapes, improving efficiency and handling non-convex features better than traditional techniques.

Findings

The method outperforms traditional shape models in accuracy.

Achieved an IoU of 0.89 for concave area detection.

Validated on observational data with robust results.

Abstract

Asteroid shape inversion using photometric data has been a key area of study in planetary science and astronomical research.However, the current methods for asteroid shape inversion require extensive iterative calculations, making the process time-consuming and prone to becoming stuck in local optima. We directly established a mapping between photometric data and shape distribution through deep neural networks. In addition, we used 3D point clouds to represent asteroid shapes and utilized the deviation between the light curves of non-convex asteroids and their convex hulls to predict the concave areas of non-convex asteroids. We compared the results of different shape models using the Chamfer distance between traditional methods and ours and found that our method performs better, especially when handling special shapes. For the detection of concave areas on the convex hull, the intersection over union (IoU) of our predictions reached 0.89. We further validated this method using observational data from the Lowell Observatory to predict the convex shapes of the asteroids 3337 Milo and 1289 Kuta, and conducted light curve fitting experiments. The experimental results demonstrated the robustness and adaptability of the method