Earth surface immune system quickly detects unknown land anomalies
Earth Surface Immune System for Rapid Monitoring of Unknown Anomalies
Computer Vision and Pattern Recognition
Summary
Changing environmental conditions and human actions create many new, unpredictable problems on Earth's surface. The authors developed ESIA, a detection system inspired by the biological immune system, to spot these unknown changes using satellite images. It first finds areas that look different from before, then identifies what kind of problem it might be without predefined categories. This system adapts quickly to new locations and helps monitor disasters and environmental damage in real time.
What this means in practice
- •For disaster response teams: Rapidly detect and assess unknown environmental disasters from satellite images to guide emergency efforts.
- •For environmental monitoring agencies: Quantify damage severity and categorize unknown anomalies on Earth’s surface for ongoing environmental surveillance.
Authors
Jingtao Li, Qian Zhu, Xinyu Wang, Deren Li, Liangpei Zhang, Yanfei Zhong
Abstract
Earth surface anomalies, driven by escalating climate change, and expanding human activities, are increasing in both frequency and diversity, yet their limited historical data and unpredictability make them fundamentally different from conventional remote sensing targets. Existing methods address specific anomaly categories or stop at localization, leaving a gap between detection and actionable information. Here we present ESIA, an Earth Surface Immune System whose architecture is constrained by three principles from the biological immune system, refined over millions of years against equally diverse and uncertain threats. A non-specific innate immune stage treats anomalies as unobserved changes in time-series satellite imagery, generating binary localization maps at 14.51 km2/s without assuming any anomaly category, surpassing the strongest general baseline by 37% in F1. A specific adaptive immune stage applies negative selection to filter text prompts and matches surviving prompts with localized image patches through a multi-modal foundation model, enabling open-vocabulary recognition of unknown anomaly attributes including category, affected area, and damage severity, with recognition F1 exceeding 80%. A mutation mechanism tunes minimal embeddings at test time, adapting to each scene in 3.26s using a single reference image pair. We validate ESIA on a global-scale dataset covering 19,801.60 km2 across six anomaly categories, comparing against 22 models, and further apply it to quantify degraded farmland in the Dnipro Delta following the Kakhovka Dam collapse and assess burn severity from 2025 Palisades Fire in Los Angeles. This unprecedented flexibility in handling unknown anomalies opens new avenues for real-time disaster response and environmental surveillance.