arXiv cs.AI· Jorge L. Rodriguez, Victor Angulo Morales, Areej Alwahas, Mariana Elias Lara, Fida Mohammad Thoker, Kasper Johansen, Bernard Ghanem, Fernando T. Maestre, Matthew F. McCabe·· 5 小时前AI 评分38
FLORO：跨传感器与尺度的生态遥感多模态地理空间基础模型
FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
AI 导读
研究者提出多模态地理空间基础模型 FLORO，通过掩码自编码在 Sentinel-1、Sentinel-2、SkySAT 影像、高程与无人机数据组成的小规模高多样性语料上预训练，并以可用性感知输入适配异构传感器配置。在 PANGAEA 基准冻结编码器评测中，FLORO 取得六项分割基准平均第二名、三项场景分类基准平均第三名，并在回归任务中表现突出，适用于异构观测条件下的生态环境监测。
正文 · 原文
Abstract:Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor configurations, limiting their suitability for ecological and environmental applications, where observations often vary across platforms, spatial and spectral resolutions, and available modalities. We introduce FLORO, a multimodal geospatial foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus. FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data. To accommodate sensor variability, FLORO incorporates availability-aware inputs that indicate which spectral bands and auxiliary modalities are present in each sample, enabling a unified input space across heterogeneous sensor configurations. We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks. Despite being pretrained on a smaller corpus than competing foundation models, FLORO achieved strong and stable transfer across optical, optical-SAR, and optical-elevation benchmarks spanning medium-resolution satellite, airborne, and ultra-high-resolution UAV imagery. FLORO obtained the second-best average segmentation performance across six PANGAEA benchmarks, the third-best average rank across three scene-classification benchmarks, and excelled in regression tasks, while qualitative results showed improved preservation of spatial structure in flood, urban, biomass, and canopy-height prediction settings. Overall, these results position FLORO as a practical framework for ecological and environmental monitoring under heterogeneous sensing conditions.
| Comments: | 57 pages, 11 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.28174 [cs.CV] |
| (or arXiv:2605.28174v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.28174 arXiv-issued DOI via DataCite |
|
| Journal reference: | ISPRS Journal of Photogrammetry and Remote Sensing 243, Part 1 (2027) 811-839 |
| Related DOI: | https://doi.org/10.1016/j.isprsjprs.2026.10.008
DOI(s) linking to related resources |
Submission history
From: Jorge L. Rodríguez Galvis Mr. [view email]
[v1]
Wed, 27 May 2026 08:55:54 UTC (28,638 KB)
[v2]
Thu, 29 Oct 2026 13:22:38 UTC (32,628 KB)
来源：arXiv cs.AI · arxiv.org