年度地球观测嵌入编码野火扰动并支持简化烧毁区域制图
Annual Earth-observation embeddings encode wildfire disturbance and support simplified burned area mapping
- Conservation Research Institute, University of Cambridge（剑桥大学保护研究所）
- Department of Plant Sciences, University of Cambridge（剑桥大学植物科学系）
- dClimate Labs（dClimate实验室）
- Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）
- Department of Earth System Science, Stanford University（斯坦福大学地球系统科学系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究验证年度地球观测嵌入（如Tessera）能有效编码野火扰动，无需火灾专用影像或密集时间序列即可高精度绘制烧毁区域，并支持跨区域迁移，为简化区域制图提供新路径。
AI中文摘要：
中分辨率（10-30米）烧毁区域制图对于监测野火及其影响至关重要，但难以大规模推广。现有方法要么需要精选的火灾专用影像，要么需要密集的时间序列分析。在此，我们测试了年度地球观测嵌入是否足以保留野火扰动信号，从而在无需上述任一要求的情况下绘制烧毁区域。利用Tessera和AlphaEarth嵌入，我们测试了单个烧伤疤痕的描绘、区域内所有同年火灾的制图、区域全覆盖制图、跨大陆迁移以及年内火灾发生时间。Tessera强烈编码了野火扰动，即使线性模型也能将烧毁与未烧毁像素区分开来；而AlphaEarth中的信号较弱。基于单个Tessera嵌入训练的模型，其性能达到或超过了使用配对火灾前后HLS影像的等效模型，并且优于仅使用火灾后影像的模型。同样的方法在基准场景中绘制了所有同年火灾（F1=0.90）。在加利福尼亚州全境应用时，下游训练未使用任何加州火灾数据，该方法恢复了参考烧毁区域的97%，并检测到比GABAM或MCD64A1多得多的小型和中型火灾。另外，一个在2018-2021年美国火灾上训练的模型，无需重新训练即可迁移到2024-2025年欧洲的88起火灾（F1=0.88）。对于检测良好的火灾，点火时间的平均绝对误差为13天。在日历年年底附近点燃的火灾性能下降，且全覆盖部署在某些未见过的景观中产生了系统性误报。尽管如此，年度嵌入实现了高分割精度，同时将密集时间序列处理的负担转移到上游，为更简化的区域烧毁区域制图提供了一条有前景的路径。
英文摘要：
Medium-resolution (10-30 m) burned area mapping is vital for monitoring wildfires and their impacts, but remains difficult to scale. Existing methods require either curated fire-specific imagery or dense time-series analysis. Here, we tested whether annual Earth-observation embeddings retain wildfire disturbance signals sufficiently to map burned areas without either requirement. Using Tessera and AlphaEarth embeddings, we tested individual burn-scar delineation, mapping of all same-year fires within an area, regional wall-to-wall mapping, cross-continental transfer, and intra-annual fire timing. Tessera strongly encoded wildfire disturbance, allowing even linear models to separate burned from unburned pixels; the signal was weaker in AlphaEarth. Models trained on a single Tessera embedding matched or exceeded equivalent models using paired pre- and post-fire HLS imagery, and outperformed post-fire imagery alone. The same approach mapped all same-year fires within benchmark scenes (F1 = 0.90). Applied across California, with no California fire data used for downstream training, it recovered 97% of reference burned area and detected substantially more small and medium-sized fires than GABAM or MCD64A1. Separately, a model trained on 2018-2021 US fires transferred without retraining to 88 European fires from 2024-2025 (F1 = 0.88). For well-detected fires, ignition timing was recovered with a mean absolute error of 13 days. Performance declined for fires ignited near the end of the calendar year, and wall-to-wall deployment produced systematic false positives in some unseen landscapes. Annual embeddings nevertheless achieve high segmentation accuracy while moving the burden of dense time series processing upstream, providing a promising path towards simpler regional burned area mapping.
