What question did this study set out to answer?

The central aim is to develop a deep learning approach for detecting cosmic voids based on simulations.

February 8, 2026The Astrophysical Journal0 citationsOpen Access

DeepVoid: A Deep Learning Void Detector

SKSam Kumagai MVMichael S. Vogeley MAMiguel A. Aragón-Calvo

Key Points

The central aim is to develop a deep learning approach for detecting cosmic voids based on simulations.
Utilized deep convolutional neural networks for void detection.
Implemented U-Net architecture for training and prediction.
Used curriculum learning to improve model performance on data with larger separations.
Achieved a void F1 score of 0.96 for dark matter particles at λ = 0.33 h −1 Mpc.
Matthews correlation coefficient of 0.81 across structural classes at λ = 0.33 h −1 Mpc.
At λ = 10 h −1 Mpc, void F1 score of 0.89 and coefficient of 0.6 for subhalos.

Abstract

Abstract We present DeepVoid, an application of deep learning trained on a physical definition of cosmic voids to detect voids in density fields and galaxy distributions. By semantically segmenting the IllustrisTNG simulation volume using the tidal tensor, we train a deep convolutional neural network to classify local structure using a U-Net architecture for training and prediction. The model achieves a void F1 score of 0.96 and a Matthews correlation coefficient over all structural classes of 0.81 for dark matter particles in IllustrisTNG with interparticle spacing of λ = 0.33 h −1 Mpc. We then apply the machine learning technique of curriculum learning to enable the model to classify structure in data with significantly larger intertracer separation. At the highest tracer separation tested, λ = 10 h −1 Mpc, the model achieves a void F1 score of 0.89 and a Matthews correlation coefficient of 0.6 on IllustrisTNG subhalos.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper