HiT: History-Injection Transformers for Onboard Continuous Flood Change Detection
This work addresses flood monitoring for hazard management by enabling continuous satellite-based detection with strict memory and computational constraints, though it is incremental as it builds on existing transformer models.
The paper tackled onboard flood detection for satellites by developing a History Injection Transformer (HiT) that reduces data storage by over 99% while maintaining accuracy compared to baselines, achieving 43 FPS on Jetson Orin Nano hardware.
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