星上异常检测用于高效海洋环境监测
On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
Thomas Goudemant · Clotilde Szywala · Benjamin Francesconi · Michelle Aubrun · Yves Bobichon · Marjorie Bellizzi · et al.
中文摘要
海洋生态系统受到油溢、水华和泥沙洪灾等多种威胁的冲击，破坏了栖息地、野生动物和人类活动。卫星影像和人工智能的进步提升了此类危害的早期检测和缓解能力。本文提出一种用于配备多光谱或高光谱传感器的地球观测卫星的海洋事件检测pipeline。方法包括一个自监督神经网络编码器，将卫星图像压缩到潜在空间，实现高效星上处理。机器学习异常检测模型识别正常海况的偏差，以检测环境异常。与Isolation Forest、One-Class支持向量机和Local Outlier Factors等传统算法进行比较。我们的轻量级、资源高效pipeline针对计算资源有限的卫星进行了优化部署，从嵌入式CPU到AI硬件加速器均可运行。通过优先传输关键信息，我们的方案提升了系统响应性并优化了卫星通信带宽。通过当前在多个任务中的集成演示，包括欧洲空间局（ESA）的Phisat-2任务和Microsoft/Thales Alenia Space的IMAGIN-e任务，我们的pipeline旨在通过提供及时警报和高效数据压缩来改善海洋环境监测。
关键要点
- 01问题：海洋生态系统面临油溢、水华、泥沙洪灾等威胁，需要卫星进行早期异常检测
- 02方法：自监督神经网络编码器将多光谱/高光谱图像压缩到潜在空间，实现星上高效处理
- 03方法：机器学习异常检测模型识别偏离正常海况的模式，与Isolation Forest、One-Class SVM、Local Outlier Factors对比
- 04优势：轻量级pipeline适合部署在计算资源有限的卫星上，从嵌入式CPU到AI加速器均可运行
- 05应用：已在ESA Phisat-2和Microsoft/Thales Alenia Space IMAGIN-e任务中集成，通过优先传输关键信息优化卫星带宽
解读
尚无解读。
原始英文摘要
arXiv:2610.03649v1 Announce Type: new Abstract: Marine ecosystems are impacted by various threats such as oil spills, algal blooms, and sediment floods, which disrupt habitats, wildlife, and human activities. Advances in satellite imagery and Artificial Intelligence (AI) have enhanced our capabilities for early detection and mitigation of such hazards. In this paper, we propose a marine event detection pipeline for Earth observation satellites equipped with multi- or hyperspectral sensors. Our approach includes a self-supervised neural network encoder that compresses satellite images into a reduced latent space, enabling efficient onboard processing. A machine learning anomaly detection model identifies deviations from normal sea patterns to detect environmental anomalies. We compare its performance against traditional algorithms such as Isolation Forest, One-Class Support Vector Machine and Local Outlier Factors. Our lightweight, resource-efficient pipeline is optimized for deployment on satellites with limited computational resources, ranging from embedded CPUs to AI hardware accelerators. By prioritizing the transmission of critical information, our solution enhances system responsiveness and optimizes satellite communication bandwidth. Demonstrated through current integration across multiple missions, including European Space Agency's (ESA) Phisat-2 mission and Microsoft/Thales Alenia Space IMAGIN-e mission, our pipeline aims to improve marine environmental monitoring by providing timely alerts and efficient data reduction.