ORBITALIF：一种用于星上云去除的高效脉冲联邦学习框架
ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal
浏览论文内容
中文总结 AI 辅助
针对低轨卫星传统云去除流程的缺陷，研究人员提出OrbitALIF脉冲联邦学习框架，采用SNN骨干网络及相关模块，实现星上云去除，能耗较ANN降低72.3倍且性能相当。
中文摘要 AI 辅助
低轨（LEO）卫星可实现高分辨率、大规模的地球观测，应用于灾害监测、环境监测等领域。然而，云层覆盖常遮挡地表，传统云去除流程需将含云图像下载至地面站处理，存在通信窗口有限、星地带宽受限、延迟高等问题。本研究提出一种用于低轨星座云去除的新型卫星联邦学习框架，命名为轨道注意力泄漏积分发放（OrbitALIF）。OrbitALIF采用紧凑的2.30M参数脉冲神经网络（SNN）骨干网络，结合自适应门控融合模块（AGFM）与光谱-空间混合注意力模块（SHAM），并采用去中心化联邦学习策略，通过星间链路共享模型权重，实现星上训练与推理。实验表明，OrbitALIF在神经形态硬件上每次推理仅消耗0.287mJ能量，较等效人工神经网络（ANN）能耗降低72.3倍（98.6%），同时达到具有竞争力的云去除质量。
英文摘要
Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and environmental surveillance. However, cloud coverage often obscures the Earth's surface, and conventional cloud-removal pipelines that download cloudy images to ground stations for processing suffer from limited contact windows, constrained satellite-to-ground bandwidth, and high latency. In this work, we propose a novel satellite federated learning framework for cloud removal across LEO constellations, named orbital attention leaky integrate-and-fire (OrbitALIF). OrbitALIF performs both onboard training and inference using a compact 2.30,M-parameter spiking neural network (SNN) backbone with an adaptive gated fusion module (AGFM) and a spectral-spatial hybrid attention module (SHAM), combined with a decentralized federated learning strategy that shares model weights via inter-satellite links. Our experiments show that OrbitALIF achieves competitive cloud removal quality while consuming only 0.287,mJ per inference on neuromorphic hardware, a 72.3 times (98.6%) energy reduction versus an equivalent artificial neural network (ANN).
发表机构
- School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
