用基础模型提升生态制图精度，验证了多模态优势与数据对齐重要性。
Ecological mapping with geospatial foundation models
- 用预训练模型微调，跨生态任务实现更好泛化能力。
- 多模态输入使性能显著提升，但输入与预训练差异会降低效果。
- 高分辨率数据和精确标注对捕捉细粒度生态变化至关重要。
地球观测基础模型在高影响力生态应用中的价值尚未充分评估。本研究首次系统评估了两种常见生态应用场景的表现、局限与实际考量：森林功能特征估计、土地利用与覆盖制图、泥炭地检测。我们微调了两个预训练模型（Prithvi-EO-2.0 和 TerraMind），并使用开源数据集与 ResNet-101 基线进行对比。在所有任务中，Prithvi-EO-2.0 和 TerraMind 均持续优于基线，展现出更强的跨领域泛化与迁移能力。TerraMind 在单模态下略胜一筹，加入额外模态后表现显著提升。然而，性能对下游输入与预训练模态间的差异敏感，凸显数据对齐的重要性。结果还表明，更高分辨率输入和更精确的像素级标签对于捕捉精细尺度生态动态仍至关重要。
原文摘要 · Abstract (English)
The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the first to systematically evaluate the performance, limitations and practical considerations across three common ecological use cases: forest functional trait estimation, land use and land cover mapping and peatland detection. We fine-tune two pretrained models (Prithvi-EO-2.0 and TerraMind) and benchmark them against a ResNet-101 baseline using datasets collected from open sources. Across all tasks, Prithvi-EO-2.0 and TerraMind consistently outperform the ResNet baseline, demonstrating improved generalization and transfer across ecological domains. TerraMind marginally exceeds Prithvi-EO-2.0 in unimodal settings and shows substantial gains when additional modalities are incorporated. However, performance is sensitive to divergence between downstream inputs and pretraining modalities, underscoring the need for careful dataset alignment. Results also indicate that higher-resolution inputs and more accurate pixel-level labels remain critical for capturing fine-scale ecological dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。