Using MRNet to Predict Lunar Rock Categories Detected by Chang'e 5 Probe

2025-02-14

AI Summary

This work addresses the challenge of fine-grained, sparse-class rock identification in lunar surface imagery acquired by China’s Chang’e-5 mission in Oceanus Procellarum. To improve recognition accuracy for geologically distinct but sparsely distributed rock types, we propose MRNet—a novel end-to-end supervised learning framework. MRNet innovatively integrates an enhanced U-Net architecture with dilated convolutions into the VGG16 decoder, thereby strengthening joint modeling of global contextual information and local structural details. Evaluated on CE5ROCK, a custom dataset comprising 100 high-fidelity, pixel-level annotated lunar images, MRNet achieves state-of-the-art performance—significantly outperforming baseline models including AlexNet and MobileNet. The model is computationally efficient and lightweight, enabling practical deployment in resource-constrained lunar in-situ exploration scenarios. This study provides a scalable, deployable solution for intelligent rock classification in extraterrestrial surface analysis.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web search models and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

China's Chang'e 5 mission has been a remarkable success, with the chang'e 5 lander traveling on the Oceanus Procellarum to collect images of the lunar surface. Over the past half century, people have brought back some lunar rock samples, but its quantity does not meet the need for research. Under current circumstances, people still mainly rely on the analysis of rocks on the lunar surface through the detection of lunar rover. The Oceanus Procellarum, chosen by Chang'e 5 mission, contains various kind of rock species. Therefore, we first applied to the National Astronomical Observatories of the China under the Chinese Academy of Sciences for the Navigation and Terrain Camera (NaTeCam) of the lunar surface image, and established a lunar surface rock image data set CE5ROCK. The data set contains 100 images, which randomly divided into training, validation and test set. Experimental results show that the identification accuracy testing on convolutional neural network (CNN) models like AlexNet or MobileNet is about to 40.0%. In order to make full use of the global information in Moon images, this paper proposes the MRNet (MoonRockNet) network architecture. The encoding structure of the network uses VGG16 for feature extraction, and the decoding part adds dilated convolution and commonly used U-Net structure on the original VGG16 decoding structure, which is more conducive to identify more refined but more sparsely distributed types of lunar rocks. We have conducted extensive experiments on the established CE5ROCK data set, and the experimental results show that MRNet can achieve more accurate rock type identification, and outperform other existing mainstream algorithms in the identification performance.

Problem

• Predict lunar rock categories
• Enhance identification accuracy
• Utilize MRNet architecture

Innovation

• MRNet architecture for lunar rock identification
• VGG16 and U-Net for feature extraction
• Dilated convolution enhances rock type recognition