Automatic detection of CMEs using synthetically-trained Mask R-CNN

TL;DR

This paper presents a deep learning approach using Mask R-CNN trained on synthetic data to automatically segment and identify coronal mass ejections in coronagraph images, improving detection robustness and reducing human bias.

Contribution

The study introduces a synthetic data training framework for Mask R-CNN to enhance CME segmentation accuracy and versatility across different instruments and CME complexities.

Findings

Median IoU of 0.98 on synthetic validation images

IoU of 0.77 on real observations compared to manual segmentations

Model differentiates CMEs from background features effectively

Abstract

Coronal mass ejections (CMEs) are a major driver of space weather. To assess CME geoeffectiveness, among other scientific goals, it is necessary to reliably identify and characterize their morphology and kinematics in coronagraph images. Current methods of CME identification are either subjected to human biases or perform a poor identification due to deficiencies in the automatic detection. In this approach, we have trained the deep convolutional neural model Mask R-CNN to automatically segment the outer envelope of one or multiple CMEs present in a single difference coronagraph image. The empirical training dataset is composed of 10^5 synthetic coronagraph images with known pixel-level CME segmentation masks. It is obtained by combining quiet coronagraph observations, with synthetic white-light CMEs produced using the GCS geometric model and ray-tracing technique. We found that our model-based trained Mask R-CNN infers segmentation masks that are smooth and topologically connected. While the inferred masks are not representative of the detailed outer envelope of complex CMEs, the neural model can better differentiate a CME from other radially moving background/foreground features, segment multiple simultaneous CMEs that are close to each other, and work with images from different instruments. This is accomplished without relying on kinematic information, i.e. only the included in the single input difference image. We obtain a median IoU=0.98 for 1.6*10^4 synthetic validation images, and IoU=0.77 when compared with two independent manual segmentations of 115 observations acquired by the COR2-A, COR2-B and LASCO C2 coronagraphs. The methodology presented in this work can be used with other CME models to produce more realistic synthetic brightness images while preserving desired morphological features, and obtain more robust and/or tailored segmentations.