Deep learning framework for crater detection and identification on the Moon and Mars

2025-08-05

AI Summary

This study addresses the low detection accuracy and poor scale adaptability of automated impact crater detection on the Moon and Mars. We propose a two-stage deep learning framework: Stage I employs ResNet-50 for high-precision detection of large craters (achieving mAP@0.5 = 92.3%); Stage II integrates YOLOv5 for multi-scale, end-to-end localization and classification, significantly improving recall for small craters while maintaining balanced performance (F1 = 0.86). The framework fuses multi-source remote sensing imagery (LROC and CTX) and supports morphological classification and spatial distribution statistics. Compared to single-model approaches, it achieves substantial advances in cross-planetary generalizability, scale robustness, and support for geological interpretation. The framework provides a reproducible, scalable, and intelligent paradigm for planetary surface geological evolution studies.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Impact craters are among the most prominent geomorphological features on planetary surfaces and are of substantial significance in planetary science research. Their spatial distribution and morphological characteristics provide critical information on planetary surface composition, geological history, and impact processes. In recent years, the rapid advancement of deep learning models has fostered significant interest in automated crater detection. In this paper, we apply advancements in deep learning models for impact crater detection and identification. We use novel models, including Convolutional Neural Networks (CNNs) and variants such as YOLO and ResNet. We present a framework that features a two-stage approach where the first stage features crater identification using simple classic CNN, ResNet-50 and YOLO. In the second stage, our framework employs YOLO-based detection for crater localisation. Therefore, we detect and identify different types of craters and present a summary report with remote sensing data for a selected region. We consider selected regions for craters and identification from Mars and the Moon based on remote sensing data. Our results indicate that YOLO demonstrates the most balanced crater detection performance, while ResNet-50 excels in identifying large craters with high precision.

Problem

• Automated detection of lunar and Martian impact craters
• Analysis of crater spatial distribution and morphology
• Comparison of deep learning models for crater identification

Innovation

• Uses CNN, ResNet, YOLO for crater detection
• Two-stage framework for identification and localization
• Analyzes remote sensing data from Moon and Mars