Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features
作者: Thomas Ratsakatika, Mihai Zotta, Srinivasan Keshav, Emily R. Lines
分类: cs.LG, cs.CV, eess.IV
发布日期: 2026-09-23
备注: 34 pages, including supplementary material (19-page main article with 7 figures and 3 tables; 15-page supplement with 9 figures and 21 tables). Submitted for publication. Data: https://doi.org/10.5281/zenodo.22693148 (embargoed until publication); code: https://github.com/ratsakatika/detecting-old-growth-forests
💡 一句话要点
利用地理空间嵌入技术检测古老森林并优化验证方法
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 古老森林检测 地理空间嵌入 遥感技术 生态保护 空间验证
📋 核心要点
- 现有方法在古老森林检测中面临标签稀缺和空间自相关的问题，影响了模型的准确性和可推广性。
- 论文提出利用地理基础模型（GFM）嵌入和多种特征进行古老森林的检测，并通过空间验证方法优化模型性能。
- 实验结果显示，GFM和Sentinel特征在未使用缓冲区的情况下提高了精度-召回曲线AUC，但在使用缓冲区后，优势减小，表明缓冲区的重要性。
📝 摘要（中文）
古老森林在数百年间发展，具有复杂的结构和丰富的生物多样性。本文研究了地理基础模型（GFM）嵌入在罗马尼亚南喀尔巴阡山脉的古老森林检测中的应用。通过构建高置信度的参考标签，并结合多种特征进行比较，结果表明，GFM和Sentinel特征在空间验证中提高了检测精度，但在使用10公里缓冲区后，优势有所减小。研究强调了缓冲区在转移检测模型时的重要性，并提供了未来研究所需的标签和预测数据。
🔬 方法详解
问题定义：本文旨在解决古老森林检测中的标签稀缺和空间自相关问题，现有方法在不同区域的适用性受到限制。
核心思路：通过构建高置信度的参考标签，并结合地理基础模型（GFM）嵌入和多种特征，提升古老森林的检测精度，同时引入缓冲区以减少空间自相关的影响。
技术框架：研究首先在211,893公顷的罗马尼亚南喀尔巴阡山脉构建参考标签，接着将GFM、AlphaEarth、TESSERA v2和Sentinel-1/2特征与基线特征结合，最后通过空间验证评估模型性能。
关键创新：最重要的创新在于引入缓冲区进行空间验证，发现其在转移学习中的重要性，尤其是在不同地理区域的模型适用性方面。
关键设计：在模型训练中，采用了10公里的训练-测试缓冲区以限制残余自相关，同时在10米分辨率下，卷积神经网络未能显著提升性能，显示出XGBoost在像素级别上的优势。
🖼️ 关键图片
📊 实验亮点
实验结果表明，在未使用缓冲区的情况下，TESSERA的精度-召回曲线AUC达到0.84，相较于Sentinel-1/2和AlphaEarth分别提高了0.08。然而，在10公里缓冲区下，优势减小至0.04和0.03，显示出缓冲区对模型性能的显著影响。
🎯 应用场景
该研究的潜在应用领域包括生态保护、森林管理和遥感监测等。通过准确检测古老森林，能够为生物多样性保护和可持续发展提供数据支持，促进政策制定和环境管理的科学化。未来，该方法可扩展至其他生态系统的监测与评估。
📄 摘要（原文）
Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, protecting them requires mapping that is accurate for individual forest parcels yet deployable continent-wide. Geospatial foundation model (GFM) embeddings enable label-scarce land classification, but their value for old-growth detection remains unknown. Here, we map old-growth forests across 211,893 ha of Romania's Southern Carpathians, a beech-spruce landscape typical of the Alpine Biogeographic Region. We construct high-confidence, expert-informed reference labels for old-growth and non-old-growth parcels. We add AlphaEarth, TESSERA v2 and Sentinel-1/2 features to a common baseline of topographic and human-access predictors, then compare them under spatially blocked validation with and without 10 km train-test buffers to limit residual autocorrelation. With buffering, GFM and Sentinel-1/2 predictors increase precision-recall AUC by 0.21-0.25 [95% CIs: 0.15-0.34] relative to baseline, indicating spectral data contain a spatially robust old-growth signal. With a PR-AUC of 0.84 [0.79-0.88], TESSERA outperforms Sentinel-1/2 (+0.08 [+0.05 to +0.11]) and AlphaEarth (+0.08 [+0.04 to +0.12]) under unbuffered spatial validation. At a 10 km buffer, however, this advantage narrows to +0.04 [-0.01 to +0.11] and +0.03 [-0.04 to +0.10], intervals consistent with no difference. At 10 m resolution, convolutional neural networks add no benefit over pixel-based XGBoost. Comparisons with four national- and continental-scale products show the importance of non-old-growth labels, and reveal 81% agreement between our predictions and a field-calibrated map. We conclude that buffered spatial validation is vital when transferring old-growth detection models to unseen landscapes, and provide our labels and predictions for future work.