Explainable Deep-Learning Based Potentially Hazardous Asteroids Classification Using Graph Neural Networks

• URL: http://arxiv.org/abs/2504.18605v1
• Date: Fri, 25 Apr 2025 09:49:48 GMT
• Title: Explainable Deep-Learning Based Potentially Hazardous Asteroids Classification Using Graph Neural Networks
• Authors: Baimam Boukar Jean Jacques,
• Abstract summary: Classifying potentially hazardous asteroids (PHAs) is crucial for planetary defense and deep space navigation.<n>We introduce a Graph Neural Network (GNN) approach that models asteroids as nodes with orbital and physical features, connected by edges representing their similarities.<n>Our model achieves an overall accuracy of 99% and an AUC of 0.99, with a recall of 78% and an F1-score of 37% for hazardous asteroids.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classifying potentially hazardous asteroids (PHAs) is crucial for planetary defense and deep space navigation, yet traditional methods often overlook the dynamical relationships among asteroids. We introduce a Graph Neural Network (GNN) approach that models asteroids as nodes with orbital and physical features, connected by edges representing their similarities, using a NASA dataset of 958,524 records. Despite an extreme class imbalance with only 0.22% of the dataset with the hazardous label, our model achieves an overall accuracy of 99% and an AUC of 0.99, with a recall of 78% and an F1-score of 37% for hazardous asteroids after applying the Synthetic Minority Oversampling Technique. Feature importance analysis highlights albedo, perihelion distance, and semi-major axis as main predictors. This framework supports planetary defense missions and confirms AI's potential in enabling autonomous navigation for future missions such as NASA's NEO Surveyor and ESA's Ramses, offering an interpretable and scalable solution for asteroid hazard assessment.

Related papers

• Towards LLM Agents for Earth Observation [49.92444022073444]
  We introduce datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors. Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time. We improve the failure rate for open models by fine-tuning synthetic data, allowing much smaller models to achieve comparable accuracy to much larger ones.
  arXiv  Detail & Related papers  (2025-04-16T14:19:25Z)
• A multi-model approach using XAI and anomaly detection to predict asteroid hazards [0.3749861135832073]
  This work offers a sophisticated method for accurately predicting hazards by combining machine learning, deep learning, explainable AI (XAI), and anomaly detection.<n>A hybrid algorithm improves prediction accuracy by combining several cutting-edge models.<n>Timely mitigation is made possible by a real-time alarm system that notifies worldwide monitoring stations.
  arXiv  Detail & Related papers  (2025-03-20T07:00:01Z)
• NEOviz: Uncertainty-Driven Visual Analysis of Asteroid Trajectories [41.49140717172804]
  We introduce NEOviz, an interactive visualization system designed to assist planetary defense experts in the visual analysis of near-Earth objects. In particular, we present a novel approach for visualizing the 3D uncertainty region through which an asteroid travels. For potential impactors, we combine the 3D visualization with an uncertainty-aware impact map to illustrate the potential risks to human populations.
  arXiv  Detail & Related papers  (2024-11-05T05:04:12Z)
• Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning [72.86540018081531]
  Unlabeled motion planning involves assigning a set of robots to target locations while ensuring collision avoidance. This problem forms an essential building block for multi-robot systems in applications such as exploration, surveillance, and transportation. We address this problem in a decentralized setting where each robot knows only the positions of its $k$-nearest robots and $k$-nearest targets.
  arXiv  Detail & Related papers  (2024-09-29T23:57:25Z)
• Deep-learning based measurement of planetary radial velocities in the presence of stellar variability [70.4007464488724]
  We use neural networks to reduce stellar RV jitter in three years of HARPS-N sun-as-a-star spectra. We find that the multi-line CNN is able to recover planets with 0.2 m/s semi-amplitude, 50 day period, with 8.8% error in the amplitude and 0.7% in the period.
  arXiv  Detail & Related papers  (2023-04-10T18:33:36Z)
• Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions [49.79068659889639]
  Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by traversability. We present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking. We also present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix.
  arXiv  Detail & Related papers  (2021-09-12T12:52:20Z)
• Prediction of Apophis Asteroid Flyby Optimal Trajectories and Data Fusion of Earth-Apophis Mission Launch Windows using Deep Neural Networks [0.0]
  The Earth-Apophis mission is driven by additional factors and scientific goals beyond the unique opportunity for natural experimentation. understanding the strength and internal integrity of asteroids is not just a matter of scientific curiosity. This paper presents a conceptual robotics system required for efficiency at every stage from entry to post-landing.
  arXiv  Detail & Related papers  (2021-04-11T21:42:53Z)
• Artificial Neural Network classification of asteroids in the M1:2 mean-motion resonance with Mars [0.0]
  We use artificial neural networks to identify asteroid orbits affected by the M1:2 mean-motion resonance with Mars. Our model was able to perform well above 85% levels for identifying images of asteroid resonant arguments. Using supervised machine learning methods, optimized through the use of genetic algorithms, we also predicted the orbital status of all multi-opposition asteroids in the area.
  arXiv  Detail & Related papers  (2021-03-29T13:03:47Z)
• A Two-Stage Deep Learning Detection Classifier for the ATLAS Asteroid Survey [0.0]
  We present a two-step neural network model to separate detections of solar system objects from optical and electronic artifacts. We show that the model reaches 99.6% accuracy on real asteroids in ATLAS data with a 0.4% false negative rate.
  arXiv  Detail & Related papers  (2021-01-22T01:35:08Z)
• On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems [62.997667081978825]
  We present a formal framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. The first class involves adversarial examples and concerns the introduction of small perturbations of the input data that cause misclassification. The second class, introduced here for the first time and named stealth attacks, involves small perturbations to the AI system itself.
  arXiv  Detail & Related papers  (2020-04-09T10:56:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.