arXiv Computer Vision September 18, 2026 By Jingtao Li, Qian Zhu, Xinyu Wang, Deren Li, Liangpei Zhang, Yanfei Zhong

Earth Surface Immune System for Rapid Monitoring of Unknown Anomalies

Read the original on arXiv Computer Vision →

The paper introduces ESIA, an Earth Surface Immune System that detects and recognizes unknown anomalies in satellite imagery without prior category knowledge. It uses a non‑specific innate stage for rapid localization and a specific adaptive stage that matches image patches to text prompts via a multi‑modal model, achieving high F1 scores. The system adapts to new scenes in seconds and has been validated on a large global dataset, with applications to farmland degradation after the Kakhovka Dam collapse and burn severity assessment from the 2025 Palisades Fire.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning

Aug 4

Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams

arXiv:2608. 00012v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated.

By Fengxiang Wang, Qiuyang Yu, Yueying Li, Mingshuo Chen, Chengchi Fei, Kaiyi Xu, Lixin Gu, Wangxu Wei, Junchao Gong, Lipeng Ma, Jiong Wang, Fenghua Ling, Wenlong Zhang, Xue Yang, Wenjing Yang, Ben Fei, Long Lan

llms multimodal benchmarks

arXiv Machine Learning

Oct 5

A Two-Stage Cascade for Near-Real-Time Forest Anomaly Detection from Sentinel-1 SAR Time Series

The paper presents a two‑stage cascade for near‑real‑time detection of forest anomalies using Sentinel‑1 SAR time series. The first stage applies an adaptive robust‑statistics z‑score test on co‑registered VH backscatter against a same‑season historical baseline, while the second stage uses a convolutional autoencoder’s structural similarity metric to confirm disturbances. Alerts are issued only when both stages agree, with confidence scores and risk tiers based on repeat‑occurrence history, and the system outputs area estimates compatible with MRV workflows.

By Pann Thinzar Seint, Subas Chhatkuli, Bryan Atwood

arXiv Computer Vision

Sep 2

A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation Data

arXiv:2609.01514v1 Announce Type: cross Abstract: Historically, retrieving rainfall data from satellite imagery has been the domain of space agencies. However, in recent years, the development of che...

By Andres F. Monsalve, Hernan A. Moreno, Christian D. Kummerow

computer-vision benchmarks

arXiv AI

Oct 15

EarthAlign: Learning Language-Aligned Representations of Earth System Data

arXiv:2610.14624v1 Announce Type: cross Abstract: Interpreting Earth system conditions is central to understanding environmental risks and informing decisions across weather- and climate-sensitive se...

By Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma, Dat Tien Nguyen, Youssef Wehbe, Duncan Watson-Parris, Salman Khan

rag nlp multimodal safety

arXiv AI

Jun 16

Near--Real-Time Conflict-Related Fire Detection in Sudan Using Unsupervised Deep Learning

arXiv:2512. 07925v4 Announce Type: replace-cross Abstract: Ongoing armed conflict in Sudan highlights the need for rapid monitoring of conflict-related fire-affected areas.

By Kuldip Singh Atwal, Dieter Pfoser, Daniel Rothbart

rag

arXiv Computer Vision

Oct 12

Revisiting the Task of Building Damage Assessment by Satellite Imaging

The paper revisits building damage assessment (BDA) from satellite imagery, emphasizing the need for a sensor‑agnostic, instance‑based task definition that can handle missing pre‑event data. It reviews existing datasets by modality, timing, and geography, critiques current single‑score evaluation practices, and proposes a more robust, ranking‑based multi‑score protocol. The authors also survey deep learning methods, highlight challenges in generalizing to new events and regions, and outline how these insights could shape future BDA challenges and data‑sharing practices.

By Anthony Cioppa, Virgile Blua, S\'ebastien Pi\'erard, Pietro Ceccato, Marc Van Droogenbroeck

computer-vision