Natural disaster monitoring through continuous satellite observation requires processing multi-temporal data under strict operational constraints. This paper addresses flood detection, a critical application for hazard management, by developing an onboard change detection system that operates within the memory and computational limits of small satellites. We propose History Injection mechanism for Transformer models (HiT), that maintains historical context from previous observations while reducing data storage by over 99\% of original image size. Moreover, testing on the STTORM-CD flood dataset confirms that the HiT mechanism within the Prithvi-tiny foundation model maintains detection accuracy compared to the bitemporal baseline. The proposed HiT-Prithvi model achieved 43 FPS on Jetson Orin Nano, a representative onboard hardware used in nanosats. This work establishes a practical framework for satellite-based continuous monitoring of natural disasters, supporting real-time hazard assessment without dependency on ground-based processing infrastructure. Architecture as well as model checkpoints is available at https://github.com/zaitra/HiT-change-detection

翻译：通过连续卫星观测进行自然灾害监测需要在严格的操作约束下处理多时相数据。本文针对灾害管理中的关键应用——洪水检测，开发了一种在小型卫星内存与计算限制内运行的星上变化检测系统。我们提出了面向Transformer模型的历史注入机制（HiT），该机制在保持历史观测上下文的同时，将数据存储需求降低至原始图像大小的1%以下。在STTORM-CD洪水数据集上的测试进一步证实，集成于Prithvi-tiny基础模型的HiT机制在检测精度上可与双时相基线模型相媲美。所提出的HiT-Prithvi模型在纳米卫星典型星上硬件Jetson Orin Nano上实现了43 FPS的推理速度。本研究为基于卫星的自然灾害连续监测建立了实用框架，支持不依赖地面处理基础设施的实时灾害评估。系统架构及模型检查点已发布于https://github.com/zaitra/HiT-change-detection