Forests provide important ecosystem functions such as carbon sequestration and climate regulation, particularly in countries with high forest cover. Climate change-induced extreme weather events have a negative impact on many forest ecosystems. In Germany, for instance, the drought of the years 2018 until 2020 resulted in signs of damage in almost 80% of trees. This decline in forest vitality has additionally led to severe bark beetle infestations and widespread tree mortality, posing significant challenges to forest managers to obtain a complete picture of the state of their forests. Since a completely ground-based monitoring of forest condition is not feasible due to the forests' vast extent, remote sensing and particularly multispectral satellite image time series (SITS) analysis were suggested as efficient alternatives. Transformers, a state-of-the-art Deep Learning (DL) architecture, have shown promising results in the classification of multivariate SITS for other applications. Here, we use Transformers in combination with Sentinel-2 (S2) time series data to test if they can improve forest disturbance detection capabilities in comparison to conventional methods by automatically extracting relevant information from background variability throughout the whole time series. To match the large training data needs of Transformers, we use a two-step approach including pre-training and finetuning. During pre-training, we use outputs of earlier presented SITS approaches, while during finetuning, we use detailed reference data of known disturbances covering between 10 and 100% of a Sentinel-2 pixel as extracted from aerial images. We test three setups: DL base using ten S2 bands, DL IND using ten vegetation indices (VIs), and DL +IND utilising both as model input. F1-scores across all of our six study sites range between approx. 0.65 (DL +IND) and 0.72 (DL base) in a binary classification (undisturbed vs. disturbed) when considering both full and partial disturbances. DL base outperforms the other setups in forest disturbance detection, and detects disturbance extents as small as 40 m2 within pixels of 100 m2 size. Given the best performance of DL base, handcrafted vegetation indices (VIs) do not improve the model. Our model is competitive with existing approaches and slightly outperforms most earlier reported results, even though a direct comparison is challenging. Considering the option to further refine our trained model if additional reference data becomes available over time, we conclude that a combination of Transformers and Sentinel-2 time series can be developed into an effective tool for forest disturbance monitoring of Central European forests at fine spatial grain.

中文翻译：

---

使用变压器和 Sentinel-2 时间序列的中欧森林干扰检测


森林提供重要的生态系统功能，例如碳封存和气候调节，尤其是在森林覆盖率高的国家。气候变化引发的极端天气事件对许多森林生态系统产生了负面影响。例如，在德国，2018 年至 2020 年的干旱导致近 80% 的树木出现受损迹象。森林活力的下降还导致了严重的树皮甲虫侵扰和广泛的树木死亡，对森林管理者全面了解森林状况构成了重大挑战。由于森林面积广，完全基于地面的森林状况监测是不可行的，因此建议将遥感，特别是多光谱卫星图像时间序列 （SITS） 分析作为有效的替代方案。Transformers 是一种最先进的深度学习 （DL） 架构，在其他应用的多变量 SITS 分类中显示出有希望的结果。在这里，我们将 Transformers 与 Sentinel-2 （S2） 时间序列数据结合使用，以测试与传统方法相比，它们是否可以通过从整个时间序列的背景变化中自动提取相关信息来提高森林干扰检测能力。为了满足 Transformer 的大量训练数据需求，我们使用了两步法，包括预训练和微调。在预训练期间，我们使用之前提出的 SITS 方法的输出，而在微调期间，我们使用从航空图像中提取的已知干扰的详细参考数据，覆盖 Sentinel-2 像素的 10% 到 100%。我们测试了三种设置：使用 10 个 S2 波段的 DL 基础，使用 10 个植被指数 （VI） 的 DL IND，以及使用两者作为模型输入的 DL +IND。 当考虑完全和部分干扰时，我们所有六个研究地点的 F1 分数在大约 0.65 （DL +IND） 和 0.72 （DL 基础） 之间，采用二元分类（不受干扰与受干扰）。DL base 在森林干扰检测方面优于其他设置，可在 100 m2 大小的像素内检测小至 40 m2 的干扰范围。鉴于 DL base 的最佳性能，手工制作的植被指数 （VIs） 并不能改善模型。我们的模型与现有方法相比具有竞争力，并且略优于大多数早期报告的结果，尽管直接比较具有挑战性。考虑到随着时间的推移有额外的参考数据可用，可以选择进一步改进我们的训练模型，我们得出结论，Transformers 和 Sentinel-2 时间序列的组合可以发展成为一种有效的工具，用于在细小空间颗粒下对中欧森林进行森林干扰监测。