Leveraging Satellite Image Time Series for Accurate Extreme Event Detection

TL;DR

This paper introduces SITS-Extreme, a new satellite image time series framework that improves early detection of extreme weather events by filtering irrelevant changes and focusing on disaster signals, validated through extensive experiments.

Contribution

The paper presents a novel satellite image time series framework for extreme event detection, demonstrating significant improvements over existing bi-temporal methods and analyzing its scalability and component contributions.

Findings

Substantial performance improvements over bi-temporal baselines.

Effective filtering of irrelevant changes in satellite data.

Scalable and applicable across different disaster types.

Abstract

Climate change is leading to an increase in extreme weather events, causing significant environmental damage and loss of life. Early detection of such events is essential for improving disaster response. In this work, we propose SITS-Extreme, a novel framework that leverages satellite image time series to detect extreme events by incorporating multiple pre-disaster observations. This approach effectively filters out irrelevant changes while isolating disaster-relevant signals, enabling more accurate detection. Extensive experiments on both real-world and synthetic datasets validate the effectiveness of SITS-Extreme, demonstrating substantial improvements over widely used strong bi-temporal baselines. Additionally, we examine the impact of incorporating more timesteps, analyze the contribution of key components in our framework, and evaluate its performance across different disaster types, offering valuable insights into its scalability and applicability for large-scale disaster monitoring.