Deep machine learning for meteor monitoring: advances with transfer learning and gradient-weighted class activation mapping
arXiv:2310.16826 · doi:10.1016/j.pss.2023.105802
Abstract
In recent decades, the use of optical detection systems for meteor studies has increased dramatically, resulting in huge amounts of data being analyzed. Automated meteor detection tools are essential for studying the continuous meteoroid incoming flux, recovering fresh meteorites, and achieving a better understanding of our Solar System. Concerning meteor detection, distinguishing false positives between meteor and non-meteor images has traditionally been performed by hand, which is significantly time-consuming. To address this issue, we developed a fully automated pipeline that uses Convolutional Neural Networks (CNNs) to classify candidate meteor detections. Our new method is able to detect meteors even in images that contain static elements such as clouds, the Moon, and buildings. To accurately locate the meteor within each frame, we employ the Gradient-weighted Class Activation Mapping (Grad-CAM) technique. This method facilitates the identification of the region of interest by multiplying the activations from the last convolutional layer with the average of the gradients across the feature map of that layer. By combining these findings with the activation map derived from the first convolutional layer, we effectively pinpoint the most probable pixel location of the meteor. We trained and evaluated our model on a large dataset collected by the Spanish Meteor Network (SPMN) and achieved a precision of 98\%. Our new methodology presented here has the potential to reduce the workload of meteor scientists and station operators and improve the accuracy of meteor tracking and classification.
Accepted in Planetary and Space Science
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Grad-CAM: Why did you say that?
- The Global Meteor Network -- Methodology and First Results
- Orbital characterization of superbolides observed from space: dynamical association with near-Earth objects, meteoroid streams and identification of hyperbolic meteoroids
- Accurate 3D fireball trajectory and orbit calculation using the 3D-FireTOC automatic Python code
- Perfect density models cannot guarantee anomaly detection
- Learning about comets from the study of mass distributions and fluxes of meteoroid streams
- Luminous efficiency based on FRIPON meteors
- Identifying meteorite droppers among the population of bright 'sporadic' bolides imaged by the Spanish Meteor Network during the spring of 2022
- Object classification on video data of meteors and meteor-like phenomena: algorithm and data
- AI-Enhanced Data Processing and Discovery Crowd Sourcing for Meteor Shower Mapping