Current Synthetic Aperture Radar (SAR)-based flood detection methods face critical limitations that hinder operational deployment. Supervised learning approaches require extensive labeled training data, exhibit poor geographical transferability, and may fail to adapt to new regions without additional training examples. Existing approaches do not fully exploit the rich temporal information available in SAR time series, instead relying on simple change detection between pre- and post-flood images or supplementary datasets that often introduce error propagation. These limitations prevent effective automated flood monitoring in data-scarce regions where disaster response is most needed. To address these limitations, we develop a novel training-free approach by adapting Bayesian analysis for change point problems, specifically for automated flood detection from Sentinel-1 Ground Range Detected time series data. Our method statistically models the temporal behavior of SAR backscatter intensity over a one-year baseline period, then computes the posterior probability of change points at flood observation dates. This approach eliminates supervised learning dependencies by using Bayesian inference to identify when backscatter deviations exceed expected normal variations, leveraging inherent statistical properties of time series data. Validation across three diverse geographical contexts using the UrbanSARFloods benchmark dataset demonstrates superior performance compared to conventional thresholding and deep learning approaches, achieving F1 scores up to 0.75. This enables immediate deployment to any region with SAR coverage, providing critical advantages for disaster response.

翻译：当前基于合成孔径雷达（SAR）的洪水检测方法存在关键局限性，阻碍了其业务化部署。监督学习方法需要大量标注训练数据，地理可迁移性差，且在没有额外训练样本的情况下难以适应新区域。现有方法未能充分利用SAR时间序列中丰富的时序信息，而是依赖于灾前与灾后图像间的简单变化检测或辅助数据集，后者常引入误差传播。这些局限性阻碍了在亟需灾害响应但数据稀缺区域实现有效的自动化洪水监测。为应对这些局限，我们通过将贝叶斯分析适配于变化点问题，提出了一种无需训练的新方法，专门用于从Sentinel-1地距检测（GRD）时间序列数据中实现自动洪水检测。我们的方法首先对一年基准期内SAR后向散射强度的时序行为进行统计建模，随后计算在洪水观测日期发生变化点的后验概率。该方法利用时间序列数据固有的统计特性，通过贝叶斯推断识别后向散射偏差何时超出预期的正常波动范围，从而消除了对监督学习的依赖。基于UrbanSARFloods基准数据集在三个不同地理环境下的验证表明，相较于传统阈值方法和深度学习方法，本方法取得了更优的性能，F1分数最高可达0.75。这使得该方法能够立即部署到任何具有SAR覆盖的区域，为灾害响应提供了关键优势。